---
title: RePEc papers featured by ML-Quant
url: https://www.ml-quant.com/papers/repec/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
---


# RePEc

Economics working papers from RePEc's NEP field reports.

- [Assessing the Benefits of Optimized Agentic AI Systems for Asset Pricing](https://www.ml-quant.com/papers/repec/nbr-nberwo-35431/) (2026-09-25): Optimized AI systems analyzing earnings call transcripts double explained variation in stock returns versus standard benchmarks while improving interpretability through human-readable decision rules.
- [Stablecoins Meet the Mundell–Fleming Trilemma](https://www.ml-quant.com/papers/repec/fip-fednsr-103702/) (2026-09-25): Wallet-level stablecoin data shows crisis countries experience inflows during banking restrictions; this endogenizes capital mobility and tightens monetary policy constraints.
- [Skewness Risk Premia and the Cross-Section of Currency Returns](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20587/) (2026-09-25): Using model-free skewness measures from currency options, the study shows that skewness risk is priced in currency returns and explains variation across a broad cross-section of currency portfolios.
- [The Global Credit Cycle](https://www.ml-quant.com/papers/repec/cpr-ceprdp-21268/) (2026-09-25): A nonlinear factor constructed from credit spreads and equity volatility prices global corporate bond returns, explaining up to 13% of three-month-ahead return variation across markets.
- [Asset Embeddings](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20082/) (2026-09-25): The paper shows that portfolio holdings contain all information needed for asset pricing and develops asset embeddings analogous to word embeddings to represent firms and predict valuations.
- [Pricing Risk Globally: Intermediary Constraints, the Dollar, and the Global Financial Cycle](https://www.ml-quant.com/papers/repec/fip-fedgif-103716/) (2026-09-25): A two-country model shows that uncertainty shocks tighten intermediary constraints, widening credit spreads, appreciating the dollar, and raising currency risk premia globally.
- [Carry Trade and Currency Crash Risk](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20745/) (2026-09-25): Focusing on dollar-lira trading, the paper shows that higher crash risk significantly increases carry trade expected returns, accounting for 46–77% of compensation through Shapley decomposition.
- [Predicting Financial Market Stress with Machine Learning](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20439/) (2026-09-25): Tree-based machine learning models predict the full distribution of financial market stress 27% better than traditional time-series methods, with macro uncertainty and monetary policy expectations as key drivers.
- [The credit channel of monetary policy: direct survey evidence from UK firms](https://www.ml-quant.com/papers/repec/boe-boeewp-023260/) (2026-09-25): UK firm survey data validates that external borrowers face larger cost-of-capital increases and cut investment more than internal funders when rates rise, accounting for a quarter of monetary policy's total effect.
- [Innovation, financial frictions, and persistent effects of monetary policy](https://www.ml-quant.com/papers/repec/boe-boeewp-023581/) (2026-09-25): Monetary tightening reduces R&D more sharply among firms lacking cash-flow-based borrowing, generating persistent 0.12% output loss that younger, high-patent firms bear disproportionately.
- [Ex Machina: Financial Stability in the Age of Artificial Intelligence](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20681/) (2026-09-25): Q-learning and large language model investors generate systematically different behaviors in fund redemption settings, with Q-learning showing excessive coordination and amplified fragility under default risk.
- [Elastic in cash, inelastic in repo: Hedge funds in the treasury and repo markets](https://www.ml-quant.com/papers/repec/zbw-safewp-343098/) (2026-09-25): Using German sovereign bond repo data, the research shows hedge funds are price-elastic in cash markets but highly inelastic in repo, inheriting elasticity from their cash-market counterparties.
- [HKC05 - Household Portfolios, Corporate Leverage, and the Supply Side of Monetary Policy](https://www.ml-quant.com/papers/repec/cxv-wpaper-2602/) (2026-09-25): Corporate leverage affects how monetary tightening transmits to the real economy: equity holders lose wealth while safe-asset holders are cushioned, raising the sacrifice ratio.
- [Prices and Monetary Policy: The Role of Financial Constraints](https://www.ml-quant.com/papers/repec/hhs-rbnkwp-0468/) (2026-09-25): Swedish data reveals that financially constrained firms adjust prices less to monetary shocks, materially dampening aggregate inflation response to policy changes.
- [Capturing Heterogeneity: Machine Learning Approaches to Implied Volatility Forecasting](https://www.ml-quant.com/papers/repec/fip-fedgfe-103519/) (2026-09-25): Tree-based models partition the option surface by moneyness and maturity to forecast volatility, reducing one-month-ahead errors by 13 percent versus benchmark models.
- [Capital flows and exchange rates: A quantitative assessment of the dilemma hypothesis](https://www.ml-quant.com/papers/repec/boe-boeewp-023263/) (2026-09-25): In response to US monetary tightening, financial channels dominate for small open economies: credit spreads widen and output falls despite currency depreciation.
- [Rate Risk and Rate Insurance](https://www.ml-quant.com/papers/repec/nbr-nberwo-35636/) (2026-09-25): Stock returns are dampened by rate insurance: falling rates cushion payoff risk in bad times while rising rates in good times hedge duration exposure.
- [Common Risk Factors in the Returns on Stocks, Bonds (and Options), Redux](https://www.ml-quant.com/papers/repec/nbr-nberwo-35579/) (2026-09-25): The research identifies common risk factors spanning stocks, corporate bonds, and options linked to economic indicators, revealing significant market segmentation and cross-asset hedging opportunities.
- [Credit Card Banking](https://www.ml-quant.com/papers/repec/nbr-nberwo-35607/) (2026-09-25): Analysis of 550 million US credit card accounts shows that despite high charge-off rates, card lenders earn 1.5% alpha and 6.8% return on assets through pricing power and non-interest income.
- [Bank Runs With and Without Bank Failure](https://www.ml-quant.com/papers/repec/nbr-nberwo-35504/) (2026-09-25): A database of 3,984 historical US bank runs shows runs are more likely in weak banks but often occur in strong banks; failures concentrate in fundamentally weak institutions.
- [Taming Volatility, Feeding Crashes: Evidence from Algorithmic Trading in China's Agricultural Futures Markets](https://www.ml-quant.com/papers/repec/ags-aaea26-404354/) (2026-09-25): The study finds that algorithmic trading lowers realized volatility but increases tail co-movement and asymmetry in China's corn and soybean futures markets.
- [LASH Risk and Interest Rates](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20158/) (2026-09-25): The study measures liquidity risk from solvency hedging in sterling repo and swaps, finding that pre-crisis LASH risk predicted pension fund bond sales during the 2022 UK market stress.
- [Sovereign vs. Corporate Debt and Default: More Similar Than You Think](https://www.ml-quant.com/papers/repec/cpr-ceprdp-20100/) (2026-09-25): Analysis of 20 years of US junk bonds and emerging market sovereign debt reveals surprisingly similar average returns, Sharpe ratios, default frequencies, and haircuts across the two asset classes.
- [How Economic News Drives Implied Volatility in Agricultural Commodity Markets](https://www.ml-quant.com/papers/repec/ags-asea26-404810/) (2026-09-25): Financial and macroeconomic news topics systematically predict implied volatility in corn and soybean markets, with program trading and 2008 crisis topics most robust at short horizons.
- [Exogenous Risk, Hedging Pressure, and Risk Premia in Agricultural Commodity Markets](https://www.ml-quant.com/papers/repec/ags-aaea26-404411/) (2026-09-25): Traders place 15% weight on USDA crop reports relative to private priors when forming price expectations, with this anchoring weight rising when private analyst disagreement increases.
- [Collateral policy surprises](https://www.ml-quant.com/papers/repec/zbw-bubdps-343110/) (2026-09-25): Expansionary central bank collateral policy surprises reduce bank default risk and volatility while compressing government bond spreads, transmitting effects distinctly from asset purchases.
- [Adaptive LASSO-MGARCH for Multivariate Volatility Forecasting](https://www.ml-quant.com/papers/repec/cdf-wpaper-2026-4/) (2026-09-25): Introducing coefficient-specific penalization into multivariate GARCH equations reduces complexity and improves out-of-sample covariance forecasts across bonds, equities, and commodities.
- [Pension Liquidity Risk](https://www.ml-quant.com/papers/repec/cpr-ceprdp-21095/) (2026-09-25): Dutch pension funds use interest rate swaps more aggressively when underfunded, exposing themselves to margin calls exceeding 6% of assets and forcing procyclical sales of government bonds.
- [A theory of bank liquidity requirements](https://www.ml-quant.com/papers/repec/ecb-ecbwps-20263252/) (2026-09-25): The study develops a general equilibrium model of financial intermediation showing that liquidity regulation alone cannot achieve efficient allocations and requires complementary policies like bank size limits.
- [Systemic at Home: the Persistence of a Too-Big-to-Fail Premium in Europe](https://www.ml-quant.com/papers/repec/dnb-dnbwpp-868/) (2026-09-25): European banks with assets exceeding half of home GDP enjoy at least 30 percent lower credit spreads, and this implicit subsidy persists and depends on sovereign fiscal strength.
- [Forecast Disagreement & Risk Premia](https://www.ml-quant.com/papers/repec/eee-ecolet-v-247-y-2025-i-c-s0165176524006037/) (2025-10-27): Disagreement in macro forecasts raises risk premia: consumption disagreement hurts overall stock returns, while productivity disagreement particularly damages small, low-profit firms.
- [Target-Benefit Pension Optimization with Jumps](https://www.ml-quant.com/papers/repec/eee-insuma-v-121-y-2025-i-c-p-100-110/) (2025-10-27): Provides closed-form rules for the best benefit payouts and investment choices for a target‑benefit pension fund facing continuous and jump risks to maximize expected utility.
- [Early Exercise and Put Risk Premia](https://www.ml-quant.com/papers/repec/inm-ormnsc-v-71-y-2025-i-2-p-1824-1845/) (2025-10-27): Accounting for optimal early exercise, American puts show less negative raw returns but more negative delta‑hedged returns than European puts, changing which option anomalies look profitable.
- [Sustainable Returns and Long-Horizon Metrics](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-81-y-2025-i-1-p-33-62/) (2025-10-27): Defines a “sustainable return” (a withdrawal rate that preserves real capital) and shows that return-sequence risk and reinvesting interim cashflows are key for long-term outcomes beyond simple short-period averages.
- [Gamified Emotion Crowdsourcing](https://www.ml-quant.com/papers/repec/gam-jsoctx-v-15-y-2025-i-3-p-54-d-1597256/) (2025-10-27): The J-Plus gamified app collects emotional speech to train better emotion-recognition systems while teaching and motivating users.
- [Abstract Classification: SVM vs BERT vs GPT-3.5](https://www.ml-quant.com/papers/repec/spr-scient-v-130-y-2025-i-1-d-10-1007-s11192-024-05217-7/) (2025-10-27): SVM vs BERT vs GPT-3.5: Compares SVM, SPECTER, BERT, and GPT-3.5 for classifying abstracts: BERT performs best, while GPT-3.5 is inconsistent with limited training data.
- [Spanish Anti-Abortion Networks on Twitter](https://www.ml-quant.com/papers/repec/pal-palcom-v-12-y-2025-i-1-d-10-1057-s41599-025-04568-7/) (2025-10-27): Spanish anti-abortion Twitter groups are male-led, show hateful content, and coordinate around religion and right-wing politics.
- [Demand Forecasting for New Fashion](https://www.ml-quant.com/papers/repec/wly-jforec-v-44-y-2025-i-2-p-270-280/) (2025-10-27): Fashion product demand is hard to predict, but machine learning—especially deep learning and ensembles—can make forecasts more accurate.
- [Reinforcement Learning for Hedging](https://www.ml-quant.com/papers/ssrn/3355706/) (2025-10-24): The article introduces a novel application of reinforcement learning for efficiently managing a portfolio of over-the-counter derivatives, independent of any model.
- [HighFrequency Trading Impact](https://www.ml-quant.com/papers/repec/kap-fmktpm-v-33-y-2019-i-2-d-10-1007-s11408-019-00331-6/) (2025-10-24): The paper discusses the effects of high-frequency trading on market factors like volatility, transaction costs, and liquidity, indicating varied opinions in the financial sector.
- [Nowcasting NZ GDP with ML](https://www.ml-quant.com/papers/repec/een-camaaa-2018-47/) (2025-10-24): The paper reveals that machine learning algorithms are more effective than traditional statistical models in predicting real GDP growth in New Zealand.
- [Predicting Vehicle Wait Times at Borders](https://www.ml-quant.com/papers/repec/eee-retrec-v-89-y-2021-i-c-s0739885921000068/) (2025-10-24): The study explores new data sources and machine learning techniques to forecast short-term wait times at a US-Mexico border crossing, emphasizing the difficulties of high data variability.
- [Risk Factor Validation](https://www.ml-quant.com/papers/repec/spr-jecfin-v-43-y-2019-i-1-d-10-1007-s12197-018-9438-x/) (2025-10-24): The research disputes the Fama and French three factor model, stating that size and value mimicking factors should not be seen as systematic risk factors.
- [Cost Estimation with ML](https://www.ml-quant.com/papers/repec/pkp-rocere-2019-p-64-75/) (2025-10-24): The article introduces a machine learning method for predicting software costs early in a project with high accuracy.
- [Bank Failure Prediction](https://www.ml-quant.com/papers/repec/bba-j00001-v-3-y-2024-i-1-p-129-144-d-169/) (2025-10-24): The study uses machine learning survival models to predict US bank failures, offering insights to enhance risk management in the banking sector.
- [Brazilian ML Portfolios](https://www.ml-quant.com/papers/repec/eee-ememar-v-51-y-2022-i-pb-s1566014122000085/) (2025-10-24): The research investigates the use of machine learning to predict stock returns in Brazil, showing that an Equal Risk Contribution approach greatly enhances risk-adjusted returns.
- [Multifrequency Data Fusion Model for Carbon Price Prediction](https://www.ml-quant.com/papers/repec/wly-jforec-v-44-y-2025-i-2-p-436-458/) (2025-03-20): The newly introduced MFF-CPPM model in China has demonstrated higher accuracy and flexibility in predicting carbon trading prices compared to current models.
- [Adaptive Market Hypothesis & Sharpe Ratio Strategies](https://www.ml-quant.com/papers/repec/pkp-teafle-v-12-y-2025-i-1-p-120-142-id-4102/) (2025-03-05): The research finds that trading strategies based on the Sharpe Ratio are more profitable than the buy-and-hold strategy in global markets, supporting the Adaptive Market Hypothesis.
- [Novel Window Analysis for HFT](https://www.ml-quant.com/papers/repec/kap-compec-v-65-y-2025-i-2-d-10-1007-s10614-023-10528-7/) (2025-03-05): The study introduces a new window analysis method for assessing decision-making units' efficiency, using the Whale Optimization Algorithm, and applies it to forex investment strategies and utility firms in the Ho Chi Minh City Stock Exchange.
- [Monitoring Poverty in Data-Deprived Lebanon](https://www.ml-quant.com/papers/repec/bla-revinw-v-71-y-2025-i-1-n-e12708/) (2025-03-05): The paper uses a new data augmentation technique to study poverty in the Middle East and North Africa, specifically Lebanon, using alternative data sources when traditional income data is scarce or unavailable.
- [Estimating Convex Production Technologies](https://www.ml-quant.com/papers/repec/eee-ejores-v-323-y-2025-i-1-p-224-240/) (2025-03-05): The research adapts Stochastic Gradient Boosting for Data Envelopment Analysis to estimate production possibility sets, reducing overfitting and satisfying shape constraints, as proven by simulations and a PISA example.
- [News Sentiment and Investment Risk](https://www.ml-quant.com/papers/repec/eee-ecolet-v-247-y-2025-i-c-s0165176524006086/) (2025-03-05): The research reassesses the effect of news sentiment on stock return volatility, finding that both positive and negative firm-specific and macroeconomic news significantly impact intraday stock return volatility, with GPT-4 potentially outperforming RavenPack in classification accuracy.
- [Improved xG Model for Football](https://www.ml-quant.com/papers/repec/taf-tjorxx-v-76-y-2025-i-1-p-1-13/) (2025-03-05): The study enhances the prediction performance of the expected goal model in football analytics by integrating data from various sources and using a supervised machine learning approach, resulting in significant improvements in sensitivity, F1 metrics, and AUC metric.
- [Machine Learning for M&A](https://www.ml-quant.com/papers/repec/eee-finana-v-99-y-2025-i-c-s1057521925000201/) (2025-03-05): Machine learning models are more effective than traditional methods in predicting Chinese corporate merger and acquisition activities.
- [Tail Risk Management](https://www.ml-quant.com/papers/repec/eee-jomega-v-133-y-2025-i-c-s0305048324002135/) (2025-03-05): Two new deep learning frameworks have been proposed for estimating financial risk measures, which are more efficient than existing methods.
- [Monetary Policy Frictions and Nonperforming Loans](https://www.ml-quant.com/papers/repec/eee-ecofin-v-76-y-2025-i-c-s106294082400278x/) (2025-03-05): The study uses machine learning to analyze the impact of a monetary policy frictions index on commercial banks' nonperforming loans, advocating for more transparency in monetary policy transmission.
- [Housing Market Connectedness](https://www.ml-quant.com/papers/repec/eee-jimfin-v-152-y-2025-i-c-s0261560625000014/) (2025-03-05): The research uses machine learning and quantile connectedness models to study the international housing market, emphasizing the significant influence of the US housing market and its interest rates.
- [Oil Price Forecasting: Machine Learning vs Deep Learning](https://www.ml-quant.com/papers/repec/spr-annopr-v-345-y-2025-i-2-d-10-1007-s10479-023-05400-8/) (2025-03-05): Machine Learning vs Deep Learning: The study reveals that deep learning methods, particularly the long short-term memory approach, are more effective than machine learning methods like the support vector machine in predicting oil prices, especially during crises.
- [AI Capability Firm Performance](https://www.ml-quant.com/papers/repec/spr-infosf-v-26-y-2024-i-6-d-10-1007-s10796-023-10460-z/) (2025-03-05): The research indicates that AI capability directly affects firm performance, with a data-driven culture and AI infrastructure playing key roles.
- [Dark Patterns in Retail](https://www.ml-quant.com/papers/repec/mul-jqmthn-doi-10-1435-115112-y-2024-i-3-p-499-531/) (2025-03-05): The article discusses the problem of dark patterns in retail investment and the potential of AI and behavioral sciences in enhancing regulation.
- [Young Informal Workers](https://www.ml-quant.com/papers/repec/vrs-jsesro-v-13-y-2024-i-2-p-82-97-n-1005/) (2025-03-05): The study profiles young informal workers in the EU27, aiming to understand the impact of Covid-19 on youth labor market informality.
- [Determinants of Bank Performance](https://www.ml-quant.com/papers/repec/bco-ncafaa-v-9-y-2023-p-26-41/) (2025-03-05): The paper suggests new research areas in understanding banks' performance, focusing on digital transformation, AI, and the effects of COVID-19.
- [WNSS in Gig Work](https://www.ml-quant.com/papers/repec/cta-jcppxx-4241/) (2025-03-05): The study investigates the relevance of the Work Need Satisfaction Scale for online gig workers, proposing modifications to better suit online platform work.
- [BRM for Predictions with Missing Patterns](https://www.ml-quant.com/papers/repec/inm-orijds-v-4-y-2025-i-1-p-85-99/) (2025-02-26): The blockwise reduced modeling (BRM) method is introduced to analyze incomplete data, using ensemble models to reduce data imputation and enhance predictive performance.
- [EGovernance and Citizen Participation: A Review](https://www.ml-quant.com/papers/repec/src-sbseec-v-6-y-2024-i-3-p-317-336/) (2025-02-26): A Review: The review explores the link between e-governance initiatives and citizen participation, identifying success factors and emphasizing the need for interdisciplinary research to assess their effectiveness.
- [Enhanced Emerging Market Portfolio Performance](https://www.ml-quant.com/papers/repec/spr-fininn-v-11-y-2025-i-1-d-10-1186-s40854-025-00754-3/) (2025-02-19): A second-generation Automated Adaptive Trading System could help stabilize emerging markets during downturns, addressing challenges posed by algorithmic trading and passive investing.
- [Volatile KSE-30 Equities Allocation](https://www.ml-quant.com/papers/repec/spr-snopef-v-6-y-2025-i-1-d-10-1007-s43069-025-00421-4/) (2025-02-19): Machine learning has been used to identify assets contributing to downward trends in the Pakistan Stock Exchange, suggesting a portfolio optimization strategy for effective asset allocation.
- [Portfolio Optimization with Risk Parity](https://www.ml-quant.com/papers/repec/bla-jtsera-v-46-y-2025-i-2-p-353-377/) (2025-02-19): A new risk parity portfolio optimization method considers fat-tailed and heteroscedastic asset returns, reducing portfolio turnover during market turmoil and enhancing risk-adjusted returns.
- [Mellin Transform Approach for American Options](https://www.ml-quant.com/papers/repec/gam-jmathe-v-13-y-2025-i-3-p-479-d-1581067/) (2025-02-19): A new method for calculating option Greeks using the Mellin transform is introduced, offering a fresh approach to risk mitigation in option trading.
- [New Momentum Strategy for Equity Prediction](https://www.ml-quant.com/papers/repec/wly-jforec-v-44-y-2025-i-2-p-424-435/) (2025-02-19): The new machine learning strategy, N-MDIS, has been introduced to enhance the accuracy of equity premium prediction, outperforming previous methods.
- [Market Competition and Zero-Leverage Policies](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-18-y-2025-i-2-p-73-d-1582023/) (2025-02-19): Research indicates that increased product market competition leads firms, particularly those with high earnings volatility, to adopt zero-leverage policies, emphasizing the impact of earnings volatility on capital structure decisions.
- [Bond Market Volatility Forecasting for Chinese Stocks](https://www.ml-quant.com/papers/repec/wly-jforec-v-44-y-2025-i-2-p-547-555/) (2025-02-19): The study shows that the fluctuation of 10-year treasury bond contracts can predict China's stock market volatility, with machine learning methods proving more accurate than traditional models.
- [Stochastic Lot Streaming and Scheduling with Machine Learning](https://www.ml-quant.com/papers/repec/taf-uiiexx-v-57-y-2025-i-4-p-408-422/) (2025-02-19): The article proposes a new algorithm and machine learning model for the Lot Streaming and Scheduling Problem (LSSP) with uncertain product arrival times, aiming to enhance efficiency and precision.
- [Multiscale Dynamics in Chinese Financial Markets](https://www.ml-quant.com/papers/repec/taf-tjorxx-v-76-y-2025-i-1-p-97-110/) (2025-02-19): The paper introduces a new statistical machine learning method for breaking down and analyzing complex time series, proving its effectiveness on financial data from the COVID-19 pandemic, suggesting it could replace traditional methods.
- [Differential Returns in Germany](https://www.ml-quant.com/papers/repec/zbw-ifsowp-309421/) (2025-02-19): The study uses machine learning to analyze rates of return on wealth in Germany, revealing a negative return for the bottom 50% when adjusted for inflation and interest, with socio-economic factors predicting wealth distribution.
- [Predicting VIX Trends](https://www.ml-quant.com/papers/repec/taf-quantf-v-24-y-2024-i-12-p-1857-1873/) (2025-02-19): The study uses machine learning to predict the CBOE Volatility Index, finding that weekly jobless claim data significantly impacts market volatility and improves trading strategies' resilience.
- [Stock Price Prediction in Eurozone Banks](https://www.ml-quant.com/papers/repec/vls-finstu-v-28-y-2024-i-4-p-29-42/) (2025-02-19): The paper compares the effectiveness of different models in predicting European banking sector stock prices, concluding that traditional machine learning models outperform advanced deep learning models.
- [Lessons from Social Media for Climate Policy](https://www.ml-quant.com/papers/repec/cup-nierev-v-266-y-2023-i-p-22-29-3/) (2025-02-19): The study uses machine learning to analyze social media discussions on climate change and suggests diverse policies for net-zero goals.
- [AI Techniques for Cloud Resource Management](https://www.ml-quant.com/papers/repec/das-njaigs-v-6-y-2024-i-1-p-397-408-id-262/) (2025-02-19): The paper discusses the use of AI techniques to improve resource management in cloud environments, boosting DevOps workflows' performance and efficiency.
- [Strategic AI Governance in Moldova](https://www.ml-quant.com/papers/repec/awf-journl-y-2024-i-2-p-33-53/) (2025-02-19): The article suggests a framework for AI governance in Moldova to meet EU standards, highlighting the role of responsible AI governance in supporting Moldova's EU aspirations.
- [Covariance Matrix Shrinkage](https://www.ml-quant.com/papers/repec/eee-ecmode-v-144-y-2025-i-c-s0264999324003389/) (2025-02-05): The study suggests an optimal shrinkage intensity selection for the linear shrinkage estimator family, which results in more stable covariance matrix estimators and improves global minimum-variance portfolios.
- [Improved Cryptocurrency Volatility Predictions](https://www.ml-quant.com/papers/repec/eee-ecmode-v-144-y-2025-i-c-s0264999324003432/) (2025-02-05): The study reveals that combining different forecasting models can greatly enhance the accuracy of predicting cryptocurrency volatility. This can provide crucial information for investors looking to improve risk management strategies in cryptocurrency markets.
- [Table Tennis Network Metrics](https://www.ml-quant.com/papers/repec/eee-chsofr-v-191-y-2025-i-c-s0960077924014450/) (2025-02-05): The research uses machine learning to predict table tennis game outcomes based on new technical-tactical style metrics, demonstrating superior predictive accuracy.
- [Random Forest Choice Models](https://www.ml-quant.com/papers/repec/spr-empeco-v-68-y-2025-i-1-d-10-1007-s00181-024-02646-4/) (2025-02-05): The paper introduces the Ordered Forest, a new machine learning estimator for ordered choice models, which estimates conditional choice probabilities and marginal effects.
- [Machine Learning for Sales Prediction](https://www.ml-quant.com/papers/repec/bjf-journl-v-9-y-2024-i-12-p-623-628/) (2025-02-05): Machine learning, specifically gradient boosting, can accurately predict e-commerce sales, influenced by pricing, promotions, and seasonal factors.
- [Bullion as Hedge for Oil](https://www.ml-quant.com/papers/repec/rfb-journl-v-16-y-2024-i-1-p-33-41/) (2025-02-05): Gold and silver served as a medium-term investment hedge for crude oil during the Russia-Ukraine war, but only a weak safe haven during periods of conflict.
- [Trading Strategies in Markets](https://www.ml-quant.com/papers/repec/agh-journl-v-25-y-2024-i-2-p-117-131/) (2025-02-05): The article examines the potential and risks of money market trading in the Swiss banking sector, considering the impact of Basel III on cash trading and outlining the necessary skills for money market traders.
- [Selective Inflation Forecasting](https://www.ml-quant.com/papers/repec/aob-wpaper-62/) (2025-02-05): The research indicates that using machine learning in inflation forecasting can enhance prediction accuracy, particularly in volatile economic conditions.
- [China Fund Performance](https://www.ml-quant.com/papers/repec/idn-journl-v-27-y-2024-i-4f-p-697-720/) (2025-02-05): The study reveals a negative link between the cost of Chinese managed equity funds and their performance, suggesting a need for expense reduction reforms.
- [TimeVarying Fama-French Model](https://www.ml-quant.com/papers/repec/rfb-journl-v-16-y-2024-i-2-p-309-357/) (2025-02-05): The research identifies time-variable parameters in the Five-Factor Model, which could affect the model's central asset pricing mechanism.
- [English Translation of Thirukural](https://www.ml-quant.com/papers/repec/bcp-journl-v-8-y-2024-i-3s-p-5936-5949/) (2025-02-05): The paper compares the accuracy of Microsoft Translation and Human Translation in translating Thirukural, an ancient Tamil text, into English.
- [South Africa's Economic Challenges](https://www.ml-quant.com/papers/repec/ers-ijebaa-v-xii-y-2024-i-4-p-72-86/) (2025-02-05): The study uncovers a complex interplay between corruption, political instability, inflation, and exchange rate changes in South Africa, highlighting the need for holistic policy solutions.
- [Private Assets in Portfolio Approach](https://www.ml-quant.com/papers/repec/aza-jsoc00-y-2025-v-17-i-2-p-130-141/) (2025-01-23): The Total Portfolio Approach (TPA) enhances investment returns by diversifying risk factors, particularly beneficial in private markets.
- [Factor Model for Equity Risk](https://www.ml-quant.com/papers/repec/eee-jbfina-v-171-y-2025-i-c-s0378426624002875/) (2025-01-23): A new model using instrumented principal component analysis (IPCA) predicts country equity risk premia better than other models, especially in emerging markets.
- [Feature Importance in Financial Models](https://www.ml-quant.com/papers/repec/eee-finlet-v-71-y-2025-i-c-s1544612324014351/) (2025-01-23): Machine Learning can produce misleading results in financial models that assume linearity, indicating the need for careful application.
- [Model Specification for Volatility Forecasting](https://www.ml-quant.com/papers/repec/eee-finana-v-97-y-2025-i-c-s1057521924007828/) (2025-01-23): The best model for forecasting asset price volatility should use the natural logarithmic form of the original volatility measure for efficient regression estimators.
- [Safe Havens for Cryptocurrencies](https://www.ml-quant.com/papers/repec/spr-fininn-v-11-y-2025-i-1-d-10-1186-s40854-024-00686-4/) (2025-01-23): High-performing US tech stocks, like FAANG, can offer diversification and act as safe havens for cryptocurrency investors.
- [Dynamic Portfolio Choice with Risk Control](https://www.ml-quant.com/papers/repec/eee-ejores-v-322-y-2025-i-1-p-325-340/) (2025-01-23): In a complete market, using Value-at-Risk (VaR) increases losses while Expected Shortfall (ES) reduces losses during market downturns.
- [Systemic Risk from Overlapping Portfolios](https://www.ml-quant.com/papers/repec/eee-finana-v-97-y-2025-i-c-s1057521924007269/) (2025-01-23): A portfolio optimization framework accounting for systemic and individual risk reveals potential inefficiencies in portfolio structures, indicating a risk trade-off.
- [BRICS Stock Volatility](https://www.ml-quant.com/papers/repec/gam-jijfss-v-13-y-2025-i-1-p-8-d-1564897/) (2025-01-23): The study identifies factors affecting stock price volatility in BRICS countries during crises using data analysis, with the Random Tree method proving most effective.
- [Risk Spillovers Among Markets](https://www.ml-quant.com/papers/repec/eee-finlet-v-71-y-2025-i-c-s1544612324013138/) (2025-01-23): The paper finds that asset price declines are more consistent in extreme market conditions, based on an exploration of dependencies among commodity futures, stock markets, and ESG bond markets.
- [Volatility Indexes and Investments](https://www.ml-quant.com/papers/repec/eee-finana-v-97-y-2025-i-c-s1057521924007944/) (2025-01-23): The research reveals that the COVID-19 pandemic significantly impacted the dynamic connectedness between volatility indexes and worldwide ESG leaders’ equity markets.
- [Green Bonds and Russia Ukraine](https://www.ml-quant.com/papers/repec/eee-riibaf-v-74-y-2025-i-c-s0275531924005270/) (2025-01-23): The paper finds that green inclusive bonds showed stronger resilience to the Russia-Ukraine conflict compared to standard green bonds.
- [Bitcoin ETF Impact](https://www.ml-quant.com/papers/repec/eee-finana-v-97-y-2025-i-c-s1057521924007427/) (2025-01-23): The study finds that ETF asset managers became the major long-side participants following the introduction of the ProShares bitcoin strategy ETF.
- [Volatility Spillover in Financial Systems](https://www.ml-quant.com/papers/repec/eee-riibaf-v-74-y-2025-i-c-s0275531924004938/) (2025-01-23): The research reveals that volatility spillovers in dual financial systems form as intersectoral clusters affected by their own volatility.
- [Model-Free Price Movements](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-18-y-2025-i-1-p-30-d-1565621/) (2025-01-23): The paper introduces a model-free lattice model that can describe the complete price evolution of an asset and re-price all of its European options simultaneously.
- [Economic Policy Uncertainty and Exchange Rate](https://www.ml-quant.com/papers/repec/eee-finana-v-97-y-2025-i-c-s1057521924007567/) (2025-01-23): The study finds that the spillover effect of economic policy uncertainty on real effective exchange rate volatility is stronger in emerging markets than in developed markets.
- [Determinants of Zero-Leverage](https://www.ml-quant.com/papers/repec/eee-finlet-v-71-y-2025-i-c-s154461232401345x/) (2025-01-23): The study uses machine learning to identify factors influencing the zero-leverage phenomenon, including cash holdings, tangible assets, industry leverage-level, and firm size, and suggests a solution for sample imbalance.
- [Predicting Bond Returns](https://www.ml-quant.com/papers/repec/eee-jbfina-v-171-y-2025-i-c-s0378426624002863/) (2025-01-23): Machine learning models show strong bond return predictability, especially during high risk aversion and slow economic growth, emphasizing the importance of using both cross-sectional and time-series predictors.
- [Robust SVM Optimization](https://www.ml-quant.com/papers/repec/eee-ejores-v-322-y-2025-i-1-p-237-253/) (2025-01-23): The paper introduces new optimization models for Support Vector Machine for classification tasks, using robust optimization techniques to guard against data perturbations, and demonstrates the benefits through real-world datasets.
- [DataDriven Inventory Control](https://www.ml-quant.com/papers/repec/eee-ejores-v-322-y-2025-i-1-p-254-269/) (2025-01-23): The paper suggests a Prescriptive Analytics approach for data-driven dynamic inventory control of large product portfolios, using a 'global learning' model that outperforms 'local learning' strategies, and highlights the importance of contextual information.
- [Detecting Asset Price Bubbles using Deep Learning](https://www.ml-quant.com/papers/repec/bla-mathfi-v-35-y-2025-i-1-p-74-110/) (2025-01-23): The article discusses a deep learning algorithm designed to detect financial asset bubbles using observed call option prices. This algorithm was tested on tech stock market data and under different models.
- [Asymmetric Volatility in Crypto Currency and Stock Market](https://www.ml-quant.com/papers/repec/rfb-journl-v-16-y-2024-i-1-p-7-19/) (2025-01-23): Research shows a cointegration between major cryptocurrencies and Indian stock market indices, with cryptocurrencies reacting to stock market shocks.
- [Portfolio Optimization and ESG Risk Scores](https://www.ml-quant.com/papers/repec/blg-msudev-v-16-y-2024-i-2-p-1-13-n-1/) (2025-01-23): The paper reveals that optimal portfolio structures are influenced by ESG Risk Scores under the Mean-Semivariance Behavioral Hypothesis, but the impact is minimal.
- [Real Estate Features and Prices in Szczecin, Poland](https://www.ml-quant.com/papers/repec/vrs-remava-v-32-y-2024-i-4-p-105-116-n-1009/) (2025-01-23): The study uses Partial Dependence Plots to analyze real estate features in Szczecin, Poland, highlighting its effectiveness in understanding complex property price relationships.
- [Improving Location Analytics with Explainable AI](https://www.ml-quant.com/papers/repec/taf-rjerxx-v-46-y-2024-i-4-p-421-443/) (2025-01-23): The paper presents the SHAP location score, a new data-based method for assessing real estate locations, enhancing traditional urban models and benefiting real estate stakeholders.
- [EuroStoxx 50 Futures: Persistence](https://www.ml-quant.com/papers/repec/taf-oaefxx-v-12-y-2024-i-1-p-2302639/) (2025-01-23): Persistence: The study suggests that EuroStoxx 50 futures prices are not always efficient, with potential for abnormal profits at intraday frequency.
- [Beating Diversification Strategies](https://www.ml-quant.com/papers/repec/cup-jfinqa-v-59-y-2024-i-8-p-3601-3632-3/) (2025-01-23): The research indicates that the $1/N$ rule is best in high-dimensionality but can be improved by combining it with other rules or machine learning portfolios.
- [AIs Impact on Assets](https://www.ml-quant.com/papers/repec/bpj-evoice-v-21-y-2024-i-2-p-363-370-n-1010/) (2025-01-23): The article explores the benefits and risks of using artificial intelligence in asset management, including improved research and decision-making but potential biases.
- [Predicting Social Welfare with ML](https://www.ml-quant.com/papers/repec/taf-rsrsxx-v-11-y-2024-i-1-p-496-522/) (2025-01-23): The study finds that demographics, not income, are the key predictors of social welfare and inequality in Madrid's neighbourhoods.
- [Decision Discovery for Operations](https://www.ml-quant.com/papers/repec/spr-decisn-v-51-y-2024-i-4-d-10-1007-s40622-024-00402-2/) (2025-01-23): The paper introduces the Decision Discovery Framework (DDF) for creating decision discovery algorithms, and suggests future research on decision modeling and processing unstructured data.
- [Group Mean-Differences](https://www.ml-quant.com/papers/repec/ibn-ijspjl-v-13-y-2025-i-1-p-1/) (2025-01-15): The research proposes a compensation-factor to estimate the additional observed variables needed to recover the determinacy coefficient size after eliminating a group mean-difference, impacting the validity of the factor score predictor.
- [Impurity Functions in Trees](https://www.ml-quant.com/papers/repec/taf-lstaxx-v-54-y-2025-i-3-p-701-719/) (2025-01-15): The research disproves the similarity between impurity and concave functions in decision trees, suggesting a combination of Gini Index and Entropy may be more effective.
- [ECB Press Conference Sentiment](https://www.ml-quant.com/papers/repec/wly-ijfiec-v-30-y-2025-i-1-p-652-664/) (2025-01-15): The research uses FinBERT to analyze sentiment in ECB president's introductory statements, finding that the sentiment about monetary policy significantly affects subsequent press conference content.
- [State Equations in High-Dimensional Regression](https://www.ml-quant.com/papers/repec/taf-lstaxx-v-54-y-2025-i-3-p-850-863/) (2025-01-15): The article explores the interchangeability of various state equations in high-dimensional statistics through parameter transformations.
- [Foreign Portfolio Investment and Index Crash Risk](https://www.ml-quant.com/papers/repec/taf-oaefxx-v-12-y-2024-i-1-p-2305481/) (2025-01-15): Research shows that exchange rate fluctuations and investor sentiment significantly impact country index crash risk, while net foreign portfolio investment has minimal effect.
- [Finance Research Trends from Machine Learning](https://www.ml-quant.com/papers/repec/wly-intsec-v-19-y-2024-i-4-p-472-507/) (2025-01-15): The paper employs machine learning models to identify trends in finance research topics from 1976 to 2015, revealing growth and shrinkage in topics and a consistent pattern in topic coverage among researchers.
- [Robust Haberman Linking vs. Invariance Alignment](https://www.ml-quant.com/papers/repec/gam-jstats-v-8-y-2025-i-1-p-3-d-1559039/) (2025-01-08): The article finds that robust Haberman linking performs better than invariance alignment for factor models when item intercepts are used, with varying results for different loss functions.
- [AI in Global Higher Ed](https://www.ml-quant.com/papers/repec/igg-jismd0-v-16-y-2025-i-1-p-1-24/) (2025-01-08): Research shows China, the US, and England are leading in AI education research, with future trends including AI-VR integration, sentiment analysis, and predictive student performance models.
- [Enflasyon Öngörüsü Türkiye'de](https://www.ml-quant.com/papers/repec/ahs-journl-v-9-y-2025-i-4-p-877-895/) (2025-01-08): A study found that XGBoost performs better in predicting inflation during economic crises in Turkey with large datasets, while the ARMA model performs better with smaller datasets.
- [Gender Accuracy in Translation](https://www.ml-quant.com/papers/repec/jfr-wjel11-v-15-y-2025-i-1-p-9/) (2025-01-08): The study compares the gender accuracy in English-Arabic machine translation of two large language models, Gemini and ChatGPT, with Gemini performing better in handling gender-related translation issues.
- [Characteristics of Polarized Groups in Online Discourse](https://www.ml-quant.com/papers/repec/spr-jcsosc-v-8-y-2025-i-1-d-10-1007-s42001-024-00350-y/) (2025-01-08): The second article employs social network analysis to comprehend the traits of 'believer' and 'denier' groups in online debates, assisting in predicting information dissemination and controlling disinformation spread.
- [Imported Sovereign Risk Spillover to China](https://www.ml-quant.com/papers/repec/eee-finlet-v-70-y-2024-i-c-s1544612324013369/) (2025-01-08): The paper discovers that imported sovereign risks from developing G20 countries have a more significant impact on China under normal conditions.
- [Algorithmic Investment Strategies on Bitcoin Data](https://www.ml-quant.com/papers/repec/war-wpaper-2024-27/) (2025-01-08): The thesis demonstrates that an automated Bitcoin trading strategy built using Informer architecture and trained with the GMADL loss function is superior to other strategies.
- [Analytical Shortcuts to Portfolio Optimization](https://www.ml-quant.com/papers/repec/gam-jmathe-v-12-y-2024-i-24-p-3946-d-1544301/) (2025-01-08): The research expands on methods for nonnegative constraints in portfolio optimization, confirming the presence of both positive and negative elements in optimal solution sets.
- [Commodity Futures Selection](https://www.ml-quant.com/papers/repec/wly-jfutmk-v-45-y-2025-i-1-p-3-22/) (2025-01-01): The article finds that traditional sample covariance matrix performs better in portfolio selection than both naive allocation and advanced covariance estimators, challenging previous equity-focused studies.
- [Insider Trading Model](https://www.ml-quant.com/papers/repec/eee-apmaco-v-488-y-2025-i-c-s0096300324005812/) (2025-01-01): The article introduces a new continuous-time insider trading model, showing that a higher correlation coefficient makes the equilibrium price more informative, reducing trading intensity and the insider's expected payoff.
- [Adaptive Online Portfolio Selection](https://www.ml-quant.com/papers/repec/eee-ejores-v-321-y-2025-i-1-p-214-230/) (2025-01-01): The article introduces a new online portfolio selection strategy that considers transaction costs and uses an adaptive scheme for sequential parameter decision, yielding higher cumulative returns and competitive Sharpe ratios than existing strategies.
- [Mathematical Models for KVA](https://www.ml-quant.com/papers/repec/eee-apmaco-v-488-y-2025-i-c-s0096300324005666/) (2025-01-01): The study presents mathematical models to compute the capital valuation adjustment using market theory and suggests numerical methods for solving the related partial differential equations.
- [Stochastic Non-Dominance Measures](https://www.ml-quant.com/papers/repec/eee-ejores-v-321-y-2025-i-1-p-269-283/) (2025-01-01): The research introduces measures of stochastic non-dominance to analyze scenarios where stochastic dominance rules are not applicable, using the Wasserstein distance as the measure.
- [Selecting Factors in Time Series](https://www.ml-quant.com/papers/repec/bla-jtsera-v-46-y-2025-i-1-p-113-136/) (2025-01-01): The paper suggests a new eigenvalue ratio criterion to determine the number of factors in static approximate factor models, validating its effectiveness through a Monte Carlo study.
- [Matrix Norm Solution for Markov Reward Games](https://www.ml-quant.com/papers/repec/eee-apmaco-v-488-y-2025-i-c-s009630032400585x/) (2025-01-01): The study introduces a new method to solve Markov reward games using matrix norms, which considers all stages and actions at once, unlike traditional methods.
- [Consumer Segmentation with Language Models](https://www.ml-quant.com/papers/repec/eee-joreco-v-82-y-2025-i-c-s0969698924003746/) (2025-01-01): The research shows that Large Language Models (LLMs) can improve clustering accuracy in consumer segmentation for marketing research and can simulate consumer preferences.
- [Multi-View Locally Weighted Regression for LGD Forecasting](https://www.ml-quant.com/papers/repec/eee-intfor-v-41-y-2025-i-1-p-290-306/) (2025-01-01): The paper presents a new method for forecasting loss given default (LGD) by dividing features into groups, building individual models, and combining the results.
- [Chatbots for Political Information Verification](https://www.ml-quant.com/papers/repec/spr-jcsosc-v-8-y-2025-i-1-d-10-1007-s42001-024-00338-8/) (2025-01-01): The article finds that while both ChatGPT and Bing Chat can detect the truthfulness of political information, ChatGPT performs better and provides more nuanced responses across different languages.
- [Enhancing Consumer Satisfaction with Investment Allocation](https://www.ml-quant.com/papers/repec/eee-joreco-v-82-y-2025-i-c-s0969698924004363/) (2025-01-01): The article suggests a new method for assessing the significance of product features and their effect on customer satisfaction. This method uses online reviews and mathematical programming to aid businesses in creating investment strategies for product enhancement.
- [D Point Cloud Shape Recognition](https://www.ml-quant.com/papers/repec/eee-matcom-v-228-y-2025-i-c-p-73-86/) (2025-01-01): The article reviews the progress of geometric shape recognition research since the 1970s, emphasizing the effectiveness of the Hough transform method, but points out its drawback of discretising its parameter space because of high computational cost.
- [Algorithmic Trading in Copper Futures](https://www.ml-quant.com/papers/repec/wly-intsec-v-19-y-2024-i-4-p-589-616/) (2025-01-01): A study on algorithmic trading strategies for Futures CopperMainContinuous in the Shanghai Futures Exchange found no successful strategies, underlining the difficulty of finding profitable strategies in the volatile futures market.
- [Forecasting Exchange Rate Volatility](https://www.ml-quant.com/papers/repec/eee-intfin-v-97-y-2024-i-c-s1042443124001331/) (2025-01-01): A combined approach using financial and macroeconomic variables is the most effective for forecasting exchange rate volatility, especially when using wavelet analysis.
- [Wealth Bias in Sin Stocks](https://www.ml-quant.com/papers/repec/pal-assmgt-v-25-y-2024-i-7-d-10-1057-s41260-024-00360-5/) (2024-12-18): The research reveals a correlation between the wealth of European societies and their investment in sin stocks, with wealthier Northern European countries yielding higher returns and familiarity leading to less rejection of sin stocks.
- [Portfolio Optimization with Transfer Entropy](https://www.ml-quant.com/papers/repec/eee-finana-v-96-y-2024-i-pa-s1057521924005763/) (2024-12-18): The study incorporates transfer entropy into portfolio optimization to account for asset dependencies, showing that this method can effectively manage portfolio stability and provide a strong alternative to traditional risk measures.
- [Predicting Stock Market Crises](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-12-p-554-d-1540423/) (2024-12-18): Extreme gradient boosting (XGBoost) is the best machine learning algorithm for predicting African stock market crises, with historical stock prices and exchange rates as key predictors.
- [Corporate Governance in Financial Distress in China](https://www.ml-quant.com/papers/repec/eee-pacfin-v-88-y-2024-i-c-s0927538x24003019/) (2024-12-18): The research uses the LightGBM machine learning method to study the effect of corporate governance indicators on financial distress in Chinese public firms, identifying institutional ownership, managerial ownership, and executive compensation disparity as key indicators.
- [Digital Platform Capabilities in Data Value Unlocking](https://www.ml-quant.com/papers/repec/eee-proeco-v-278-y-2024-i-c-s0925527324002913/) (2024-12-18): The research identifies data integration, data analytics, and data productization as crucial digital platform capabilities, explaining their role in unlocking data value and promoting digital servitization in digital enterprises.
- [Machine Learning in Credit Scoring](https://www.ml-quant.com/papers/repec/eee-aosoci-v-113-y-2024-i-c-s0361368224000278/) (2024-12-18): Research in a Chinese internet company shows machine learning credit scoring models prioritize data trails over default risk, reducing human experts' role to machine learning facilitators.
- [Hybrid Machine Learning for Stock Volatility Prediction](https://www.ml-quant.com/papers/repec/eee-finana-v-96-y-2024-i-pb-s1057521924006434/) (2024-12-18): A study uses machine learning to analyze stock market volatility, finding the RF-LASSO model to be the most effective predictor.
- [Early Detection of Child Violence with ML](https://www.ml-quant.com/papers/repec/eee-cysrev-v-166-y-2024-i-c-s0190740924005048/) (2024-12-18): A paper uses machine learning to predict child abuse in Argentina, suggesting these models could help identify at-risk households early.
- [Stock Price Reaction to Managerial Soft Info](https://www.ml-quant.com/papers/repec/taf-hbhfxx-v-25-y-2024-i-4-p-481-495/) (2024-12-18): A study uses unsupervised machine learning to analyze the effect of spontaneous information shared during conference calls on company stock prices.
- [Predicting Salmon Prices with Deep Learning and Sentiment Analysis](https://www.ml-quant.com/papers/repec/eee-jocoma-v-36-y-2024-i-c-s2405851324000576/) (2024-12-18): The article discusses a study that uses deep learning models and sentiment analysis to predict salmon prices. The study found that the accuracy of predictions improved when sentiment scores from salmon-related news were included. The hybrid CNN-LSTM model performed the best in these predictions.
- [Optimal Portfolio Analysis with Stochastic Volatility](https://www.ml-quant.com/papers/repec/wsi-ijtafx-v-27-y-2024-i-05n06-n-s0219024924500237/) (2024-12-12): The article presents a method for optimizing portfolios in a volatile financial market, using an approximation method to control error and create an optimal portfolio.
- [Correlation Matrix Estimation with Reinforcement Learning](https://www.ml-quant.com/papers/repec/eee-finana-v-96-y-2024-i-pa-s1057521924005040/) (2024-12-12): The paper introduces a data-driven approach using reinforcement learning to improve the correlation and covariance matrix, demonstrating superior performance in volatility, Sharpe ratio, and downside risk.
- [Solution Uniqueness in Portfolio Optimization](https://www.ml-quant.com/papers/repec/wsi-ijtafx-v-27-y-2024-i-05n06-n-s0219024924500195/) (2024-12-12): Research on mean-deviation portfolio optimization indicates that unique Pareto-optimal profit sharing in cooperative investment and unique solutions in the Black–Litterman asset allocation model cannot be expected.
- [Equity Premium Forecasting](https://www.ml-quant.com/papers/repec/taf-quantf-v-24-y-2024-i-10-p-1445-1461/) (2024-12-12): Machine learning methods, despite their strong forecasting abilities, often underperform in predicting the equity premium due to small datasets and low signal-to-noise ratios.
- [Factors Influencing Bond Selling](https://www.ml-quant.com/papers/repec/eme-isetez-s1571-038620240000034006/) (2024-12-12): The sale of government retail bonds in the secondary market and the holding period are greatly influenced by their return performance compared to other investment options.
- [Green Finance in Economic Cycles](https://www.ml-quant.com/papers/repec/eee-tefoso-v-209-y-2024-i-c-s0040162524005900/) (2024-12-12): The deep multi-layer perceptron (DMLP) and k-nearest neighbor (KNN) machine learning models can improve economic forecasting accuracy, especially when used with cross-validation and bootstrap bagging techniques.
- [Systemic Risk in FinTech and Traditional Finance](https://www.ml-quant.com/papers/repec/taf-eurjfi-v-30-y-2024-i-18-p-2157-2190/) (2024-12-12): The study uses machine learning to identify key factors affecting systemic risk in FinTech and traditional financial institutions, including market volatility, individual stock volatility, and market capitalization, especially under extreme market conditions.
- [Timing Volatility in Portfolio Allocations](https://www.ml-quant.com/papers/repec/spt-apfiba-v-14-y-2024-i-6-f-14-6-5/) (2024-12-12): The research indicates that dynamic strategies based on timing volatilities and correlations can enhance the economic gains of non-diversified portfolios involving only crude oil or gold, due to the predictability of their volatilities and correlations.
- [Capped Volatility Swaps Pricing](https://www.ml-quant.com/papers/repec/taf-quantf-v-24-y-2024-i-9-p-1287-1300/) (2024-12-12): The article discusses the use of machine learning in determining the prices of capped volatility swaps, using unique data for validation.
- [Clustering in Financial Markets](https://www.ml-quant.com/papers/repec/ora-journl-v-33-y-2024-i-1-p-330-336/) (2024-12-12): The article reviews the use of machine learning clustering techniques in financial markets and stock investing, discussing their potential and limitations.
- [Objectionable Web Content Filtering System](https://www.ml-quant.com/papers/repec/bjf-journl-v-9-y-2024-i-11-p-51-60/) (2024-12-12): The research is focused on developing a machine learning system to block inappropriate web content and alert parents when children encounter such content.
- [Stock Return Variation Across Countries](https://www.ml-quant.com/papers/repec/eee-finana-v-96-y-2024-i-pa-s1057521924005015/) (2024-12-12): The study uses machine learning to forecast country equity returns based on market traits, identifying significant predictability and key predictors.
- [Impact of Innovation News on Illiquid Stocks](https://www.ml-quant.com/papers/repec/eme-ejimpp-ejim-07-2022-0387/) (2024-12-12): A study using machine learning found that news about product innovation significantly impacts the returns of illiquid stocks, unlike other innovation-related news.
- [Asset Pricing in Borsa Istanbul](https://www.ml-quant.com/papers/repec/eme-jespps-jes-07-2023-0357/) (2024-12-04): A study on the Turkish Stock Exchange from 2009-2020 found that the Capital Asset Pricing Model (CAPM) better predicts average excess weekly returns than the Fama-French models.
- [Stock Portfolio Construction in BIST Retail Sector](https://www.ml-quant.com/papers/repec/eco-journ1-2024-06-3/) (2024-12-04): The study uses Entropy CRITIC IDDWS and PROMETHEE methods to create an optimal stock portfolio from BIST Retail Trade Sector firms for 2022-2023, highlighting six companies as the most efficient.
- [Capital Flows in Emerging Economies](https://www.ml-quant.com/papers/repec/spr-jqecon-v-22-y-2024-i-4-d-10-1007-s40953-024-00409-7/) (2024-12-04): The article explores the correlation in gross capital inflows and outflows in emerging and developing economies, discovering that a common global factor largely influences capital flow variations, but domestic factors can also impact sensitivity to global factors.
- [Real Estate Return and Risk Forecasting](https://www.ml-quant.com/papers/repec/spr-gjorer-v-10-y-2024-i-1-d-10-1365-s41056-024-00070-4/) (2024-12-04): A forecasting model for real estate stock returns and risks shows that German real estate stocks are more affected by economic and stock market changes than the real estate market, and carry less risk than regular stocks.
- [Cross-Sectional Anomalies and Arbitrage](https://www.ml-quant.com/papers/repec/wsi-wschap-9789811290633-0004/) (2024-12-04): An extended analysis of Kaplanski's work reveals that arbitrage activity after identifying cross-sectional anomalies alters returns, indicating long-term profitability for arbitrageurs and suggesting mispricing due to investor behavior biases.
- [Forecasting Volatility in Crypto-Winter](https://www.ml-quant.com/papers/repec/spr-digfin-v-6-y-2024-i-4-d-10-1007-s42521-024-00108-1/) (2024-12-04): The research expands the use of a volatility prediction framework using LSTM and rough volatility, demonstrating its superiority over traditional models in predicting cryptocurrency volatility.
- [Regional Banknote Forecast](https://www.ml-quant.com/papers/repec/zbw-bubdps-305276/) (2024-12-04): Machine learning can enhance cash demand forecasting and inventory performance, as shown in a study involving six branches of Deutsche Bundesbank.
- [Turkey Financial Dollarization](https://www.ml-quant.com/papers/repec/spr-qualqt-v-58-y-2024-i-6-d-10-1007-s11135-024-01911-z/) (2024-12-04): Machine learning has been used to study the effect of dollarization on Turkey's monetary policy, showing a slight impact on economic growth and a possible positive link with financial deepening.
- [Model Comparison](https://www.ml-quant.com/papers/repec/ora-journl-v-2-y-2023-i-2-p-67-75/) (2024-12-04): The study finds logistic regression more efficient than decision tree models in identifying defaulted loans in Central Credit Information System data.
- [AI Impact on Society](https://www.ml-quant.com/papers/repec/aes-dbjour-v-14-y-2023-i-1-p-61-75/) (2024-12-04): The paper focuses on the influence of AI, particularly the chatbot ChatGPT, on education and the job market, based on a survey of Romanian corporate employees.
- [Real Estate Stock Inflation Resilience](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-12-p-530-d-1527108/) (2024-11-27): The Fama-French seven-factor model effectively estimates returns on Indonesian property and real estate stocks, which can hedge inflation and interest rates.
- [Algorithmic Trading Strategies](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-5-d-10-1007-s10614-023-10532-x/) (2024-11-27): Trading algorithms, both symmetric and asymmetric, are tested on stablecoin markets using machine learning to determine profit margins, with the asymmetric algorithm performing better in unbalanced markets.
- [China Business Cycle Forecasting](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-5-d-10-1007-s10614-024-10549-w/) (2024-11-27): The study uses machine learning to predict China's business cycle using various indicators, with Logistic Regression being the most successful.
- [Data and Creativity in Marketing](https://www.ml-quant.com/papers/repec/zbw-hsgmrs-306250/) (2024-11-27): The article discusses the profound influence of artificial intelligence on marketing, highlighting the importance of combining data and creativity for the future of the industry.
- [Mutual Fund Characteristics in Portugal](https://www.ml-quant.com/papers/repec/eme-sefpps-sef-07-2023-0441/) (2024-11-20): The article analyzes the performance of Portuguese mutual funds, finding that fund age and total expense ratios significantly impact domestic equity fund performance.
- [Data Prep for ML and AI](https://www.ml-quant.com/papers/repec/nwe-iitfed-y-2024-i-1-p-146-153/) (2024-11-20): The similarities between data preparation for machine learning and data warehouses can help automate the data preparation process.
- [LowFrequency Trading Algorithm](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-11-p-501-d-1516347/) (2024-11-13): The study introduces an improved algorithmic trading model that uses price indicators and a volume factor, yielding high returns with a high success rate and low maximum loss.
- [Stock Market Index Forecasting with DLWR-LSTM Model](https://www.ml-quant.com/papers/repec/eee-finlet-v-68-y-2024-i-c-s1544612324008511/) (2024-11-13): The paper presents a DLWR-LSTM model for stock index forecasting, offering consistent accuracy regardless of time series variance.
- [Volatility Forecasting: Linear vs. Nonlinear](https://www.ml-quant.com/papers/repec/eee-empfin-v-78-y-2024-i-c-s0927539824000598/) (2024-11-13): Linear vs. Nonlinear: Machine learning models were found to be effective in forecasting global stock market volatility, with simpler models performing better for volatility-timing portfolios.
- [Investors' Risk Perception](https://www.ml-quant.com/papers/repec/taf-eurjfi-v-30-y-2024-i-17-p-2032-2058/) (2024-11-13): An unsupervised machine learning algorithm analyzed corporate disclosures, finding that most risk factors decrease return volatility when disclosed.
- [Asset Pricing Uncertainty](https://www.ml-quant.com/papers/repec/eee-empfin-v-78-y-2024-i-c-s0927539824000367/) (2024-11-13): A machine learning-constructed economic uncertainty index effectively predicted stock market returns, especially during high uncertainty and sentiment periods.
- [Stress Testing US Banks with ML](https://www.ml-quant.com/papers/repec/eee-finana-v-95-y-2024-i-pc-s1057521924004083/) (2024-11-13): The article highlights the role of machine learning in improving risk analysis during stress tests, uncovering complex macro-financial connections and enhancing risk evaluation in economic downturns.
- [DeepVol: Volatility Forecasting with Dilated Causal Convolutions](https://www.ml-quant.com/papers/repec/taf-quantf-v-24-y-2024-i-8-p-1105-1127/) (2024-11-13): Volatility Forecasting with Dilated Causal Convolutions: The study introduces DeepVol, a model using Dilated Causal Convolutions, which effectively uses high-frequency data to predict next-day market volatility.
- [Index Tracking with Shapley Explanations](https://www.ml-quant.com/papers/repec/eee-finana-v-95-y-2024-i-pc-s1057521924004198/) (2024-11-13): The paper suggests using a one-dimensional Pointwise Convolutional Autoencoder and Shapley Additive Explanations for index tracking, outperforming other stock selection strategies in various financial markets.
- [Portfolio Optimization Clustering](https://www.ml-quant.com/papers/repec/eee-ecosta-v-32-y-2024-i-c-p-1-16/) (2024-11-06): The article suggests a new investment strategy using clustering techniques to minimize assets in a portfolio, potentially outperforming traditional equal weight portfolios.
- [SemiSupervised SVMs with MIQP Model](https://www.ml-quant.com/papers/repec/spr-topjnl-v-32-y-2024-i-3-d-10-1007-s11750-024-00668-w/) (2024-11-06): The paper presents a mixed-integer quadratic optimization model for classification problems, using an iterative clustering approach to enhance computational efficiency.
- [Machine Learning in Banking](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-3-d-10-1007-s10614-023-10514-z/) (2024-11-06): Machine learning was used to predict default risk in financial institutions, with bailout probability, market share, and market-to-book ratio being key variables.
- [Public Debt's Impact on Welfare](https://www.ml-quant.com/papers/repec/eee-finlet-v-69-y-2024-i-pa-s1544612324011930/) (2024-11-06): A model was used to study the effect of public debt on macroeconomic equilibrium and wealth distribution, revealing that income channel has the most significant impact on welfare changes due to public debt.
- [Gender Classification](https://www.ml-quant.com/papers/repec/spr-topjnl-v-32-y-2024-i-3-d-10-1007-s11750-024-00671-1/) (2024-11-06): The paper introduces a new stopping criterion for gender identification in biographical texts using support vector machine classifiers, with enhanced results in inflected languages.
- [Facebook User Engagement](https://www.ml-quant.com/papers/repec/cog-meanco-v12-y-2024-a-8487/) (2024-11-06): The study analyzes the use of Facebook by French political parties during the 2022 election, finding campaign themes are more influenced by traditional strategies than user engagement.
- [IFCISA: Financial Conditions Index for South America](https://www.ml-quant.com/papers/repec/eee-riibaf-v-72-y-2024-i-pa-s0275531924003003/) (2024-10-31): Financial Conditions Index for South America: An International Financial Conditions Index for South American economies (IFCI-SA) has been proposed to track financial conditions and assess the impact of global events, incorporating standard variables, sovereign debt risk premia, and regional commodity prices.
- [Naïve Bayes for Spam Detection](https://www.ml-quant.com/papers/repec/spr-aodasc-v-11-y-2024-i-6-d-10-1007-s40745-023-00479-z/) (2024-10-31): The Naive Bayes Classifier algorithm is applied to categorize emails as spam or not using Kaggle's spam mails dataset, with outcomes affected by two Laplace values.
- [AI for Innovation Analysis](https://www.ml-quant.com/papers/repec/wsi-ijimxx-v-28-y-2024-i-05n06-n-s1363919624500208/) (2024-10-31): The study offers a detailed analysis of AI, machine learning, and big data's role in fostering innovation, identifying key research themes and trends from 1991 to 2021.
- [DEA and Regression Tree for Price Estimation](https://www.ml-quant.com/papers/repec/spr-orspec-v-46-y-2024-i-4-d-10-1007-s00291-024-00774-y/) (2024-10-31): The study uses Data Envelopment Analysis to estimate product prices from a supplier's viewpoint, proposing a two-stage estimator for unobservable negotiation behavior, proven effective in an automotive supplier industry application.
- [Metaalgorithm for Portfolio Selection](https://www.ml-quant.com/papers/repec/taf-tjorxx-v-75-y-2024-i-10-p-2032-2051/) (2024-10-23): The article discusses the use of Online Gradient Update and Online Newton Update meta-algorithms in online portfolio selection, showing they can reduce risk and improve price prediction.
- [Sustainable Investments Optimization](https://www.ml-quant.com/papers/repec/spr-annopr-v-341-y-2024-i-2-d-10-1007-s10479-024-06189-w/) (2024-10-23): A new portfolio optimization approach is developed, incorporating environmental, social responsibility, and corporate governance aspects, providing an efficient alternative to large-scale covariance matrix estimation.
- [Green Bond Cost Optimization](https://www.ml-quant.com/papers/repec/wly-jforec-v-43-y-2024-i-7-p-2607-2634/) (2024-10-23): The research creates a multi-stage stochastic model to predict the issuance of green bonds, determining that the model effectively identifies the most cost-effective conditions for issuing these bonds considering various risk factors.
- [Microsoft Copilot and Finance Workforce](https://www.ml-quant.com/papers/repec/bhx-ojtijf-v-9-y-2024-i-3-p-32-41-id-1918/) (2024-10-23): The paper explores the potential impact of the AI tool, Microsoft Copilot, on the finance workforce, suggesting a future balance between automation, skill evolution, and ethical considerations.
- [Improved NHL Draft Predictions with Scouting Reports](https://www.ml-quant.com/papers/repec/bpj-jqsprt-v-20-y-2024-i-4-p-331-349-n-1006/) (2024-10-23): Large Language Models (LLMs) are being used to enhance predictions of NHL draft outcomes by extracting information from scouting report texts and combining it with on-ice statistics.
- [EU News Engagement on Facebook](https://www.ml-quant.com/papers/repec/cog-poango-v10-y-2022-i-1-p-121-132/) (2024-10-23): Study of social media engagement with EU news shows negativity increases reactions and shares but decreases comments, while emotionality decreases reactions and shares but increases comments.
- [Collusion Regulation](https://www.ml-quant.com/papers/repec/anr-reveco-v-15-y-2023-p-177-204/) (2024-10-23): The regulation of collusion, including detection, prosecution, and firm-regulator bargaining, is explored, highlighting the need for accurate legal system modeling.
- [Linear Factor Models in U.K. Stock Returns](https://www.ml-quant.com/papers/repec/kap-rqfnac-v-63-y-2024-i-3-d-10-1007-s11156-024-01286-0/) (2024-10-17): A study of U.K. stock returns found that all multifactor models are inefficient, with the eight-factor model of Chib and Zeng performing best.
- [FourFactor Model Based on Factor Momentum](https://www.ml-quant.com/papers/repec/eee-pacfin-v-87-y-2024-i-c-s0927538x24002634/) (2024-10-17): A new four-factor model based on momentum effect in China outperforms traditional models, explaining stock, industry, and regional momentum.
- [Simulated Electronic Market with Speculative Behavior](https://www.ml-quant.com/papers/repec/eee-finlet-v-67-y-2024-i-pa-s154461232400775x/) (2024-10-17): A study of an electronic market model examines the impact of trading halts and performance-based leverage limits.
- [Economic Growth Forecasting in Sverdlovsk Region](https://www.ml-quant.com/papers/repec/aiy-jnjaer-v-23-y-2024-i-3-p-674-695/) (2024-10-17): Machine learning, particularly the random forest model, is more effective in predicting the Gross Regional Product growth of Russia's Sverdlovsk region than traditional models, according to a study.
- [Online Investor Sentiment and Stock Market Risk](https://www.ml-quant.com/papers/repec/gam-jmathe-v-12-y-2024-i-20-p-3192-d-1497063/) (2024-10-17): Machine learning techniques like extreme gradient boosting and random forest are more accurate in predicting the aggregated stock market risk premium based on online investor sentiment than traditional linear models.
- [ERM Impact on Performance](https://www.ml-quant.com/papers/repec/pal-palcom-v-11-y-2024-i-1-d-10-1057-s41599-024-03871-z/) (2024-10-17): A study finds that Turkish banking firms adopting enterprise risk management see improved performance and value, and reduced risks, suggesting the use of a partial least squares regression model for predictions.
- [Stock Movement Prediction](https://www.ml-quant.com/papers/repec/wly-jforec-v-43-y-2024-i-5-p-1199-1211/) (2024-10-17): A hybrid model combining wavelet transform and multi-input LSTM proves more accurate (72.19%) in predicting the trend of the SSE composite index than other models.
- [Operational Employability Model](https://www.ml-quant.com/papers/repec/bit-bsrysr-v-15-y-2024-i-1-p-110-130-n-1006/) (2024-10-17): Croatian graduates with cultural, human, and bridging social capital, and who engaged in high-impact practices during studies, are more likely to find suitable, well-paying jobs quickly post-graduation.
- [Importance of Hyperparameters in ML](https://www.ml-quant.com/papers/repec/cup-pscirm-v-12-y-2024-i-4-p-841-848-9/) (2024-10-17): A study reveals that only 20.31% of machine learning papers in political science journals report their hyperparameters and tuning methods, indicating a need for more transparency and robustness in machine learning models.
- [News Text Analysis](https://www.ml-quant.com/papers/repec/oup-rfinst-v-36-y-2023-i-12-p-4759-4787/) (2024-10-17): A study reveals that a pricing model based on news text from The Wall Street Journal is more effective in predicting investment opportunities than traditional models, using topic modeling and latent factor analysis.
- [Regulatory Intensity](https://www.ml-quant.com/papers/repec/oup-rfinst-v-36-y-2023-i-8-p-3311-3347/) (2024-10-17): Research using administrative data and machine-learning models shows that increased regulatory intensity raises costs and discourages companies from investing and hiring, especially financially constrained firms.
- [Partisanship in Financial Regulators](https://www.ml-quant.com/papers/repec/oup-rfinst-v-36-y-2023-i-11-p-4373-4416/) (2024-10-17): Machine learning analysis of language used in Congress and new SEC rules shows a significant increase in partisanship among SEC Commissioners from 2010-2019, while the Federal Reserve Board remains relatively nonpartisan.
- [Chinese Futures Market Evolution](https://www.ml-quant.com/papers/repec/bla-ecopol-v-36-y-2024-i-3-p-1416-1449/) (2024-10-09): Research shows high-frequency and algorithmic trading in China enhances market liquidity and lowers slippage costs for investors, despite the country's unique market structure.
- [Firm Performance Prediction with Nonfinancial Disclosures](https://www.ml-quant.com/papers/repec/eme-jaeepp-jaee-07-2023-0205/) (2024-10-09): A study suggests that adding nonfinancial factors like narrative tone and corporate governance to financial prediction models can improve the accuracy of predicting company performance in the unpredictable Pakistani market.
- [Detecting Collusion in Public Procurement](https://www.ml-quant.com/papers/repec/spr-jcsosc-v-7-y-2024-i-2-d-10-1007-s42001-024-00293-4/) (2024-10-09): A new algorithm has been developed to detect collusion in auctions using public procurement data, identifying a significant number of contracts with high collusion likelihood.
- [AI and Big Data Token Herding](https://www.ml-quant.com/papers/repec/eee-riibaf-v-72-y-2024-i-pa-s027553192400299x/) (2024-10-03): Research indicates that investors tend to follow the crowd in AI and big data token markets, especially during crises, highlighting the need for regulatory intervention for market stability.
- [Bottom-up Inflation Forecast](https://www.ml-quant.com/papers/repec/bkr-journl-v-83-y-2024-i-3-p-23-44/) (2024-10-03): Machine learning methods, especially the bottom-up approach, can accurately forecast CPI inflation, as shown with Russian data.
- [Machine Learning for Forecasting Recessions](https://www.ml-quant.com/papers/repec/zbw-dicedp-303050/) (2024-10-03): The study uses machine learning to predict German business cycles, showing fewer indicators are needed to model recessions and these models are effective during quantitative easing periods.
- [Fake News Detection](https://www.ml-quant.com/papers/repec/wsi-jikmxx-v-23-y-2024-i-05-n-s0219649224500758/) (2024-09-25): The study presents a machine learning model that can detect fake news with 99% accuracy using logistic regression and feature hashing vectorisation.
- [Credit Risk Management](https://www.ml-quant.com/papers/repec/ids-ijmpra-v-17-y-2024-i-5-p-509-521/) (2024-09-25): The article examines the application of AI in creating credit scoring models by banks to assess the creditworthiness of borrowers.
- [Crude Oil Volatility Forecasting](https://www.ml-quant.com/papers/repec/wly-jforec-v-43-y-2024-i-5-p-1422-1446/) (2024-09-25): The study shows that machine learning forecasts offer superior predictions for the volatility of WTI futures prices, resulting in economic benefits.
- [Stock Prediction News Headlines](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-2-d-10-1007-s10614-023-10449-5/) (2024-09-25): This article discusses the application of machine learning and deep learning techniques to analyze financial news headlines, with the aim of identifying low volatility stocks that perform better than the Standard and Poor’s 500 Index.
- [Dynamic Portfolio Selection with Factors](https://www.ml-quant.com/papers/repec/eee-dyncon-v-167-y-2024-i-c-s0165188924001155/) (2024-09-18): A new system of factor models, which considers both return and risk, has been introduced and has shown superior performance in predicting future investment prospects compared to standard policies.
- [Reinforcement Machine Learning for Portfolio Optimization](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0010/) (2024-09-18): The chapter discusses the application of reinforcement machine learning and quadratic optimization in determining risk limits and investment portfolios, especially during the 2007-2009 financial crisis.
- [Predicting Cryptocurrency Volatility](https://www.ml-quant.com/papers/repec/eee-finlet-v-67-y-2024-i-pa-s1544612324007876/) (2024-09-18): The SHARV-MGJR model, which includes volatility leverage effects and current return data, is suggested for better prediction of cryptocurrency market volatility, surpassing GARCH-type models in tests.
- [XAI Framework for Risk Management](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0004/) (2024-09-18): The article highlights the difficulties of using machine learning models in practical risk management in banking due to their opacity and lack of explainability, and introduces a framework for leading eXplainable AI methods.
- [AI in Finance](https://www.ml-quant.com/papers/repec/wsi-wsbook-q0449/) (2024-09-18): The book provides insights into the role of artificial intelligence and machine learning in finance, linking their development to the human aspiration for automation.
- [Bot Detection for Stock Market](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0009/) (2024-09-18): The study presents a model for identifying bot activities on Twitter, demonstrating high accuracy and the ability to predict the effect of bot tweets on stock market fluctuations.
- [Sentiment Analysis in Finance](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0005/) (2024-09-18): Sentiment Analysis is used in finance to predict market trends and investment opportunities using various algorithms and metrics.
- [ML in Portfolio Management](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0001/) (2024-09-18): Despite limitations, reinforcement learning is transforming portfolio management in the finance sector.
- [Reinforcement Learning for Allocation](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0003/) (2024-09-18): Reinforcement learning, particularly deep reinforcement learning algorithms, can solve complex portfolio problems by determining investment shares in assets.
- [Decentralized Finance (DeFi) Stylized Facts](https://www.ml-quant.com/papers/repec/wsi-wschap-9781800615212-0008/) (2024-09-18): The chapter examines the rise of Decentralized Finance (DeFi) and its potential impact on traditional finance systems.
- [Hedge Fund Strategies](https://www.ml-quant.com/papers/repec/eee-ecofin-v-74-y-2024-i-c-s1062940824001657/) (2024-09-10): The study reveals that hedge funds with higher fees and minimum investments are better at hedging geopolitical risks, while global macro hedge funds excel at timing.
- [Shipping Sentiment Impact on Rates](https://www.ml-quant.com/papers/repec/eee-transe-v-189-y-2024-i-c-s1366554524002424/) (2024-09-10): The research uses language models to create sentiment indices for shipping markets, showing they can accurately predict freight rates, outperforming traditional sentiment analysis.
- [Chinese Futures Predicting BDI](https://www.ml-quant.com/papers/repec/eee-riibaf-v-71-y-2024-i-c-s027553192400240x/) (2024-09-10): The research uses a model to show that China's commodity futures can accurately predict changes in the Baltic Dry Index, aiding decision-making in the shipping industry.
- [Drought Impact on Child Growth in Africa](https://www.ml-quant.com/papers/repec/eee-wdevel-v-182-y-2024-i-c-s0305750x24001724/) (2024-09-10): The research uses remote-sensed and individual data from Sub-Saharan Africa to show that droughts significantly affect child growth, suggesting data-driven policies can help mitigate climate change effects.
- [Urban Flood Mapping in New Orleans](https://www.ml-quant.com/papers/repec/spr-nathaz-v-120-y-2024-i-11-d-10-1007-s11069-024-06609-x/) (2024-09-10): The research finds that machine learning models, particularly the Random Forest model, outperform traditional statistical models in mapping flood susceptibility in New Orleans.
- [Machine Learning for Tech Analysis](https://www.ml-quant.com/papers/repec/kap-fmktpm-v-38-y-2024-i-3-d-10-1007-s11408-024-00451-8/) (2024-09-10): The research uses machine learning to predict daily stock returns, finding improved performance with feature selection.
- [Dynamic Currency Risk Hedging](https://www.ml-quant.com/papers/repec/eee-phsmap-v-649-y-2024-i-c-s0378437124004576/) (2024-09-10): The study suggests a machine learning method for hedging foreign exchange risk in international equity portfolios, improving currency risk hedging.
- [Machine Learning and Econometrics for Real Estate](https://www.ml-quant.com/papers/repec/bla-reesec-v-52-y-2024-i-5-p-1308-1339/) (2024-09-10): The article uses a random effects model and machine learning to predict commercial real estate values, achieving a low error rate and providing useful data visualizations.
- [Financial Fraud Detection with Machine Learning](https://www.ml-quant.com/papers/repec/pal-palcom-v-11-y-2024-i-1-d-10-1057-s41599-024-03606-0/) (2024-09-10): The study reviews literature on financial fraud detection using machine learning, noting a trend towards real datasets and credit card fraud detection models.
- [Sustainable Information System for Virtual Companies](https://www.ml-quant.com/papers/repec/vrs-econom-v-12-y-2024-i-2-p-69-96-n-1009/) (2024-09-10): The paper presents a framework for managing virtual companies in smart urban environments, using Sustainable Information Systems for various business processes.
- [Validating Causal Models with Quantitative Probing](https://www.ml-quant.com/papers/repec/bpj-causin-v-11-y-2023-i-1-p-23-n-1019/) (2024-09-10): The piece introduces a new method called quantitative probing for validating causal models, showcasing its success in simulations and offering a guide for its application in causal modelling.
- [DELSTM Model for Stock Market Prediction](https://www.ml-quant.com/papers/repec/ids-ijores-v-50-y-2024-i-4-p-426-445/) (2024-09-05): A hybrid model combining LSTM and DE algorithms significantly enhances the accuracy of stock market predictions, as shown in the Bombay Stock Exchange.
- [Transfer Learning for Data-Scarce ML](https://www.ml-quant.com/papers/repec/cup-polals-v-32-y-2024-i-1-p-84-100-6/) (2024-09-05): Deep transfer learning models like BERT can greatly enhance the analysis of large political text corpora in social sciences research by reducing the need for extensive manually annotated training data.
- [Housing GANs for Housing Market Data](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-1-d-10-1007-s10614-023-10456-6/) (2024-09-05): The study presents Housing GANs, a model that generates realistic housing data, addressing the issue of scarce data in housing market research.
- [Sentiment and Herd Behavior of Private Investors](https://www.ml-quant.com/papers/repec/fru-finjrn-240406-p-95-113/) (2024-09-05): The paper examines the sentiment of private investors on online platforms and its effect on herd behavior in the Russian stock market.
- [Autoregressive Random Forests for Financial Research](https://www.ml-quant.com/papers/repec/kap-compec-v-64-y-2024-i-1-d-10-1007-s10614-023-10429-9/) (2024-09-05): The paper shows the effectiveness of Random Regression Forests for optimal lag selection in data series, outperforming other methods.
- [VIX and Global Consciousness in Market Sentiment](https://www.ml-quant.com/papers/repec/eme-jespps-jes-11-2023-0663/) (2024-09-05): The research finds a significant correlation between Global Consciousness Project data and the S&P 500 Volatility Index, suggesting its potential in predicting market sentiment.
- [Forecasting FTSE Bursa Malaysia](https://www.ml-quant.com/papers/repec/rnd-arimbr-v-16-y-2024-i-2-p-104-114/) (2024-08-28): The study uses machine learning to predict stock prices in Malaysia, finding the Sequential Minimal Optimization Regression algorithm to be most accurate.
- [Modeling Volatility](https://www.ml-quant.com/papers/repec/bla-socsci-v-105-y-2024-i-4-p-965-979/) (2024-08-21): The research shows the effectiveness of modeling compositional volatility, using German political party support and US income shares data as examples.
- [Anomalies in Cryptocurrencies](https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-8-p-351-d-1454951/) (2024-08-21): The study reveals significant changes in volatility and day-of-the-week effects on cryptocurrency returns, especially during the COVID-19 pandemic.
- [Political Instability and Stock Markets in BRICS & Türkiye](https://www.ml-quant.com/papers/repec/eme-csefzz-s1569-375920240000114016/) (2024-08-21): The research shows that political instability notably increases stock return volatility in BRICS countries and Turkey, with Turkey being particularly affected.
- [Ownership and Volatility in Stock Markets](https://www.ml-quant.com/papers/repec/eme-ijoemp-ijoem-04-2022-0710/) (2024-08-21): The research compares risk tolerance of institutional investors in China and the US, finding that US investors are more risk-averse.
- [Money Laundering: Consequences](https://www.ml-quant.com/papers/repec/eme-jmlcpp-jmlc-09-2022-0139/) (2024-08-21): Consequences: The research suggests that 1.23% of global GDP is laundered annually, negatively impacting economic and financial indicators, except inflation rates.
- [Yield Curve Forecasting Poland](https://www.ml-quant.com/papers/repec/nbp-nbpbik-v-56-y-2024-i-4-p-459-478/) (2024-08-15): The article discusses the use of PCA and LSTM machine learning methods for predicting Poland's yield curve, with LSTM providing the most accurate results.
- [Optimal Bonds Portfolio P-world](https://www.ml-quant.com/papers/repec/taf-quantf-v-24-y-2024-i-7-p-875-888/) (2024-08-15): The research establishes arbitrage-free conditions for a parametric yield curve in the P-world and presents a bonds-portfolio optimization as a stochastic control problem.
- [Predicting US Bank Failures with ML](https://www.ml-quant.com/papers/repec/taf-apeclt-v-31-y-2024-i-15-p-1353-1359/) (2024-08-15): The research shows that simple machine learning methods like the KNN model, combined with PCA, can effectively predict bank failures.
- [Impact of Personality Traits on Private Pension Participation](https://www.ml-quant.com/papers/repec/ist-journl-v-73-y-2024-i-1-p-281-314/) (2024-08-15): The study uses machine learning to examine the influence of personality traits and financial literacy on Private Pension System participation, highlighting significant factors like gender, age, and financial literacy.
- [Greek Debt Crisis Narratives](https://www.ml-quant.com/papers/repec/zbw-mpifgd-300665/) (2024-08-15): During the 2009-2015 Greek debt crisis, negative future narratives identified through text mining of newspaper articles influenced the spread of Greek bonds, indicating that perceived futures can affect investor behavior and lead to financial crises.
- [Exploiting VIX Distortions](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-78-y-2022-i-2-p-79-95/) (2024-08-15): Long-term exposure to high market volatility can lead to underestimation of volatility, creating predictable stock returns; a strategy capitalizing on this can beat a standard index portfolio.
- [CSGFM Equity Forecasting](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-78-y-2022-i-3-p-9-29/) (2024-08-15): Equity premium predictions for long-term country stocks based on a global factor model are more accurate than time-series models, resulting in substantial benefits in various developed equity markets.
- [Value of Insider Stocks](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-78-y-2022-i-1-p-79-100/) (2024-08-15): Insider trading can disclose information about the value of all securities held by the insider, indicating that even sales driven by liquidity and diversification can offer valuable insights into insider holdings.
- [Private Debt Investment Strategies](https://www.ml-quant.com/papers/repec/taf-ufajxx-v-78-y-2022-i-3-p-94-114/) (2024-08-15): The article discusses the advantages of systematic investment strategies in syndicated leveraged loans, highlighting the success of short-term momentum and valuation styles.
- [Fintech Lending Impact on Small Business Credit](https://www.ml-quant.com/papers/repec/eee-finsta-v-73-y-2024-i-c-s1572308924000755/) (2024-08-07): Fintech lenders are using alternative data and complex models to provide loans to small businesses in high-risk areas, potentially filling the credit void left by traditional lenders.
- [Carbon Risk Hedging with Beta Hedge Ratio](https://www.ml-quant.com/papers/repec/wsi-ijtafx-v-27-y-2024-i-01-n-s0219024924500067/) (2024-08-07): A new hedge strategy has been created to reduce carbon risk in diverse portfolios, which lowers carbon beta without major losses in risk-adjusted returns, making it a suitable strategy for investors and fund managers.
- [Bankruptcy Regulations in Vietnam](https://www.ml-quant.com/papers/repec/sae-sagope-v-14-y-2024-i-2-p-21582440241255676/) (2024-08-07): The research shows a consistent negative link between distress risk and corporate profitability in Vietnam, which vanishes after bankruptcy regulations are implemented.
- [Multicriteria Optimization for Deep Learning](https://www.ml-quant.com/papers/repec/spr-annopr-v-339-y-2024-i-1-d-10-1007-s10479-022-04833-x/) (2024-08-07): The study introduces a new machine learning model that reduces bias and minimizes loss function in data sets, successfully tested on digit classification.
- [Google Search Volume Index and Investor Attention](https://www.ml-quant.com/papers/repec/spr-fininn-v-10-y-2024-i-1-d-10-1186-s40854-023-00606-y/) (2024-08-07): The study finds that Google Search Volume Index can be used to predict stock market movements and volatility, improving forecasting models.
- [Machine Learning in Credit Scoring](https://www.ml-quant.com/papers/repec/eee-finsta-v-73-y-2024-i-c-s157230892400069x/) (2024-08-07): A study reveals that machine learning models using unconventional data are more efficient in predicting credit losses and defaults, particularly during economic crises.
- [Improved Crayfish Optimization for Feature Selection](https://www.ml-quant.com/papers/repec/gam-jmathe-v-12-y-2024-i-15-p-2364-d-1445421/) (2024-08-07): The newly developed Improved Binary Crayfish Optimization Algorithm (IBCOA) enhances feature selection in data mining and machine learning, thus improving classification accuracy.
- [Machine Learning in Business](https://www.ml-quant.com/papers/repec/pal-jintbs-v-55-y-2024-i-6-d-10-1057-s41267-024-00687-6/) (2024-08-07): The use of machine learning techniques in international business can address complexity and aid theory development, as per an article that also offers practical advice for implementing a machine learning process pipeline.
- [Predictor Variables with Random Forests](https://www.ml-quant.com/papers/repec/sae-jedbes-v-49-y-2024-i-4-p-595-629/) (2024-08-07): The study compares variable selection with random forests, a machine learning method, with linear models in behavioral sciences, providing practical advice.
- [Deep Learning for Newsvendor Problems](https://www.ml-quant.com/papers/repec/spr-annopr-v-339-y-2024-i-1-d-10-1007-s10479-024-05872-2/) (2024-08-07): The study uses a deep learning algorithm to effectively solve complex control models for supply and demand problems, financial risk management, and competitive scenarios, showing successful risk reduction.
- [Property Uniqueness in Real Estate Sales](https://www.ml-quant.com/papers/repec/taf-rjrhxx-v-31-y-2022-i-2-p-220-240/) (2024-08-07): Machine learning can determine the uniqueness of residential properties from ads, which can increase sale prices but also lengthen market time.
- [Corporate Governance and Failure](https://www.ml-quant.com/papers/repec/eme-jaeepp-jaee-10-2022-0283/) (2024-08-07): Palestinian companies with independent boards, institutional ownership, and high-quality external audits are less likely to fail.
- [Macroeconomic Impact of AI](https://www.ml-quant.com/papers/repec/igg-jsem00-v-11-y-2022-i-1-p-1-43/) (2024-08-07): The paper studies the effects of AI and digitalization on the macroeconomics of EU countries, including Romania, using correlation analysis and interdependence studies.
- [Generational Financial Inclusion in Kenya](https://www.ml-quant.com/papers/repec/eme-ajemsp-ajems-09-2022-0391/) (2024-08-07): Financial inclusion in Kenya varies by generation, gender, and location, with Generation Y, males, and urban residents having greater access to financial services.
- [Agency Costs in Auditor Choice](https://www.ml-quant.com/papers/repec/eme-jfrapp-jfra-11-2021-0406/) (2024-08-07): Iranian nonfinancial companies with high agency costs often choose lower-quality auditors, but this is less common if the board has more financial experts.
- [Marine accident severity prediction](https://www.ml-quant.com/papers/repec/eee-transe-v-188-y-2024-i-c-s1366554524002382/) (2024-07-31): The research presents a framework to predict the severity of marine accidents using machine learning models and a unique two-stage feature selection method.
- [Machine Learning for Real Estate Price Indices](https://www.ml-quant.com/papers/repec/kap-jrefec-v-68-y-2024-i-4-d-10-1007-s11146-022-09893-1/) (2024-07-31): The article introduces a machine learning methodology for creating property price indices, providing higher prediction accuracy but potentially biased estimations for small samples.
- [Flexible Truck Appointment System](https://www.ml-quant.com/papers/repec/ids-ijlsma-v-48-y-2024-i-2-p-244-266/) (2024-07-31): The paper proposes a machine learning model for flexible truck appointment systems in smart ports, using real-time data to identify disruptions and reschedule appointments, thus enhancing port efficiency.
- [Interior-Point Linear SVMs](https://www.ml-quant.com/papers/repec/spr-joptap-v-202-y-2024-i-1-d-10-1007-s10957-022-02103-1/) (2024-07-31): The paper uses multiple variable splitting to solve binary classification and novelty detection problems in high-dimensional data, demonstrating competitive results against other methods and specific algorithms.
- [Sparse Temporal Disaggregation](https://www.ml-quant.com/papers/repec/bla-jorssa-v-185-y-2022-i-4-p-2203-2233/) (2024-07-31): The article introduces a new method for high-frequency estimates of economic indicators, proving its effectiveness through a simulation and application to UK's GDP data.
- [AI Adoption in Competitive Markets](https://www.ml-quant.com/papers/repec/bla-econom-v-90-y-2023-i-358-p-690-705/) (2024-07-31): The paper presents AI as a tool for improved prediction in competitive markets, demonstrating that AI use can increase supply elasticity, influence equilibrium prices, and potentially benefit non-adopting firms.
- [Auditor Reliance on AI](https://www.ml-quant.com/papers/repec/bla-joares-v-60-y-2022-i-1-p-171-201/) (2024-07-31): The research explores the effect of algorithm aversion on auditor decisions, indicating that auditors tend to disregard advice from AI systems, which could be expensive for the auditing industry and financial statement users.
- [FX Options Returns Risk Factors](https://www.ml-quant.com/papers/repec/oup-revfin-v-28-y-2024-i-3-p-897-944/) (2024-07-24): Long-term straddle momentum, implied volatility, and illiquidity are identified as key predictors of cross-sectional foreign exchange options returns.

All 748: https://www.ml-quant.com/api/v1/papers/repec.json