--- title: Econometrics & Forecasting url: https://www.ml-quant.com/topics/econometrics-forecasting/ 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 --- # Econometrics & Forecasting Forecasting, time series, econometrics and nowcasting. 297 papers featured; 18 in the last 12 months. Papers featured per quarter: 2023 Q2 8, 2023 Q3 33, 2023 Q4 21, 2024 Q1 30, 2024 Q2 34, 2024 Q3 36, 2024 Q4 32, 2025 Q1 33, 2025 Q2 40, 2025 Q3 12, 2025 Q4 7, 2026 Q1 3, 2026 Q2 0, 2026 Q3 8 ## Most cited - [TKAN: Temporal Kolmogorov-Arnold Networks](https://www.ml-quant.com/papers/ssrn/4825654/): 189 citations. The article presents Temporal Kolomogorov-Arnold Networks (TKANs), a new neural network design that merges the benefits of Recurrent Neural Networks and Long Short-Term Memory for improved multistep time series forecasting. - [Robust agents learn causal world models](https://www.ml-quant.com/papers/arxiv/2402.10877/): 102 citations. The research suggests that intelligent agents must learn an approximate causal model to generalize to new domains, impacting fields like transfer learning and causal inference. - [Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues](https://www.ml-quant.com/papers/arxiv/2307.11888/): 41 citations. The study reveals that deep neural networks using linear complex-valued RNNs and MLPs can accurately approximate regular causal sequence-to-sequence maps, with complex eigenvalues near unit disk aiding in information storage. - [SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting](https://www.ml-quant.com/papers/arxiv/2404.14757/): 36 citations. The paper introduces the State Space Transformer model for time series forecasting, which effectively captures global and local patterns, offering superior performance with less memory and computational cost. - [Assumption violations in causal discovery and the robustness of score matching](https://www.ml-quant.com/papers/arxiv/2310.13387/): 35 citations. The paper evaluates the performance of recent causal discovery methods on observational data, revealing that score matching-based methods excel in difficult scenarios, setting a new evaluation standard for causal discovery methods. - [Causal Diffusion Transformers for Generative Modeling](https://www.ml-quant.com/papers/arxiv/2412.12095/): 34 citations. The article discusses Causal Diffusion, a framework that enhances diffusion models' performance and allows a seamless shift between autoregressive and diffusion generation modes, achieving top results on the ImageNet generation benchmark. - [Quantum-Enhanced Forecasting: Leveraging Quantum Gramian Angular Field and CNNs for Stock Return Predictions](https://www.ml-quant.com/papers/arxiv/2310.07427/): 32 citations. Quantum-Enhanced Forecasting for Time Series: The study introduces a time series forecasting method, Quantum Gramian Angular Field (QGAF), that merges quantum computing and deep learning to enhance the accuracy of time series classification and forecasting, and validates its effectiveness using major stock market datasets. - [Retail Demand Forecasting: A Comparative Study for Multivariate Time Series](https://www.ml-quant.com/papers/arxiv/2308.11939/): 28 citations. The study creates improved retail demand prediction models using macroeconomic factors and past sales data. - [Supervised autoencoder MLP for financial time series forecasting](https://www.ml-quant.com/papers/arxiv/2404.01866/): 27 citations. The study investigates the use of supervised autoencoders in improving financial forecasting through precise parameter tuning. - [The econometrics of happiness: Are We Underestimating the Returns to Education and Income?](https://www.ml-quant.com/papers/arxiv/1807.11835/): 27 citations. Value Rounding Behavior: The study addresses the issue of response scale simplification in surveys, particularly by less educated respondents, and introduces a model to estimate latent subjective wellbeing. - [Diffusive Gibbs Sampling](https://www.ml-quant.com/papers/arxiv/2402.03008/): 24 citations. The article introduces Diffusive Gibbs Sampling (DiGS), a new method for sampling from multi-modal distributions, which performs better in tasks like Bayesian neural networks and molecular dynamics. - [Stock Price Prediction Using a Hybrid LSTM-GNN Model: Integrating Time-Series and Graph-Based Analysis](https://www.ml-quant.com/papers/arxiv/2502.15813/): 22 citations. A new hybrid model combining long-short-term memory networks and Graph Neural Networks enhances the accuracy of stock market predictions by capturing temporal patterns and complex inter-stock relationships, surpassing traditional and advanced benchmarks. ## Latest - [The Impossible Trinity of Time-Series Validation: A Conservation Law among Training Sufficiency, Test Coverage, and Temporal Causality](https://www.ml-quant.com/papers/arxiv/2609.29530/) (2026-09-25): Proves that training sufficiency, test coverage, and temporal causality cannot be maximized simultaneously in time-series validation, pricing each constraint explicitly. - [Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting](https://www.ml-quant.com/papers/arxiv/2609.25617/) (2026-09-25): A hierarchical multi-task framework jointly predicts price movement, volatility and volume using liquidity-aware signals, outperforming neural and tree-based baselines on Chinese equity indices. - [Stealing profits: Spread-based temporal hierarchy forecasting for day-ahead electricity markets](https://www.ml-quant.com/papers/arxiv/2609.23223/) (2026-09-25): Jointly reconciling hourly price and spread forecasts improves intraday electricity price prediction accuracy by up to 19.7% and battery-arbitrage profits by up to 10.4%. - [Nonlinear Drivers of Macroeconomic Tail Risk: A Threshold Stochastic Volatility-in-Mean VAR with Regime-Dependent Leverage](https://www.ml-quant.com/papers/arxiv/2609.26994/) (2026-09-25): A regime-switching volatility-in-mean VAR reveals that the drivers of growth and inflation tails differ from median dynamics, with macroeconomic uncertainty playing a larger role in downside risk. - [A Stochastic Nested Fixed Point Algorithm for Large-Scale BLP Estimation](https://www.ml-quant.com/papers/arxiv/2609.23998/) (2026-09-25): A stochastic nested fixed-point estimator reduces memory and computational cost for random-coefficients logit demand models, enabling estimation on 100 million markets in hours. - [The "Rough" HAR Model](https://www.ml-quant.com/papers/arxiv/2609.21587/) (2026-09-25): Augmenting HAR with a negative moving-average component approximates rough dynamics, outperforming classical models out-of-sample and matching continuous-time rough model accuracy. - [Network Realized GARCH--Itô Models: Volatility Spillovers with High-Frequency Identification](https://www.ml-quant.com/papers/arxiv/2609.29515/) (2026-09-25): Introduces a network realized GARCH-Itô model that identifies dynamic volatility transmission among assets using high-frequency data, outperforming recursive forecasts on sector ETFs. - [Industry Information and Equity Return Predictability](https://www.ml-quant.com/papers/ssrn/7486138/) (2026-09-25): Using production, employment, and sales data across 426 industries, the research shows that upstream industry signals predict aggregate monthly stock returns with 23.8% out-of-sample R-squared. - [Discounted Sales of Expiring Perishables: Challenges for Demand Forecasting in Grocery Retail Practice](https://www.ml-quant.com/papers/arxiv/2602.04464/) (2026-02-12): Including discounted sales of soon-to-expire perishables in demand forecasts leads to underestimating demand, highlighting the need for better forecasting to reduce inventory waste in grocery stores. - [Directional-shift Dirichlet ARMA models for compositional time series with structural break intervention](https://www.ml-quant.com/papers/arxiv/2601.16821/) (2026-02-02): The article introduces a new Bayesian model that analyzes compositional time series data, effectively handling structural breaks and enhancing forecasting accuracy during these changes. - [History Is Not Enough: An Adaptive Dataflow System for Financial Time-Series Synthesis](https://www.ml-quant.com/papers/arxiv/2601.10143/) (2026-01-16): A new adaptive data management system enhances model performance in quantitative finance by constantly updating to reflect market changes, addressing the shortcomings of relying solely on historical data. - [Sample Size Issues in Finance Research](https://www.ml-quant.com/papers/ssrn/4463148/) (2025-12-28): The study promotes the use of Bayesian statistics in finance to better analyze large AI-generated datasets and mitigate misleading significance from traditional methods. - [A3T-GCN for FTSE100 Components Price Forecasting](https://www.ml-quant.com/papers/arxiv/2511.21873/) (2025-12-01): A combined A3T-GCN model enhances the accuracy of FTSE100 stock price forecasts by using technical indicators and optimized sequences. - [Blameocracy: Causal Rhetoric in Politics](https://www.ml-quant.com/papers/arxiv/2504.06550/) (2025-11-12): U.S. Causal Rhetoric: Growing blame/credit language in congressional tweets changed donation patterns, fueled protests and polarization, and shifted public trust. - [FinCARE: Financial Causal Analysis with Reasoning and Evidence](https://www.ml-quant.com/papers/arxiv/2510.20221/) (2025-10-27): KG+LLM for Financial Causal Discovery: Combines SEC knowledge graphs, LLM reasoning, and causal discovery to build more accurate finance‑grounded causal models. - [Robust Optimization in Causal Models and G-Causal Normalizing Flows](https://www.ml-quant.com/papers/arxiv/2510.15458/) (2025-10-27): We show interventionally robust optimization is continuous under a G‑causal Wasserstein distance and introduce a causal normalizing flow that respects this, improving data augmentation for causal prediction and portfolio optimization. - [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. - [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. - [Predicting Market Troughs: A Machine Learning Approach with Causal Interpretation](https://www.ml-quant.com/papers/arxiv/2509.05922/) (2025-09-13): The research uses machine learning to identify that the volatility of options-implied risk and market liquidity are key factors causing market lows, challenging simpler models. - [Chaotic Bayesian Inference: Strange Attractors as Risk Models for Black Swan Events](https://www.ml-quant.com/papers/arxiv/2509.08183/) (2025-09-13): The paper presents a risk model that combines heavy-tailed priors with chaotic dynamics to predict volatility clustering, fat tails, and extreme events, providing a dual perspective for systemic risk analysis. - [FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model](https://www.ml-quant.com/papers/arxiv/2509.08742/) (2025-09-13): Multi-modal Forecasting: FinZero, a pre-trained model fine-tuned by the Uncertainty-adjusted Group Relative Policy Optimization method, is introduced in the article, enhancing the accuracy, adaptability, and scalability of financial time series forecasting. - [Forecasting Probability Distributions of Financial Returns with Deep Neural Networks](https://www.ml-quant.com/papers/arxiv/2508.18921/) (2025-08-29): The research shows that deep neural networks can accurately forecast financial return distributions and are competitive with traditional models for risk assessment and portfolio management. - [FinCast: A Foundation Model for Financial Time-Series Forecasting](https://www.ml-quant.com/papers/arxiv/2508.19609/) (2025-08-29): Time-Series Forecasting Model: FinCast, a new model for financial time-series forecasting, outperforms existing methods by effectively capturing diverse patterns without needing domain-specific adjustments. - [The Coherent Multiplex: Scalable Real-Time Wavelet Coherence Architecture](https://www.ml-quant.com/papers/arxiv/2508.19994/) (2025-08-29): Wavelet Coherence Architecture: The Coherent Multiplex system uses a multilayer graph to identify and analyze coherence among multiple time series in real-time, with potential uses in neuroscience, finance, and biomedical signal analysis. - [Stealing accuracy: Predicting day-ahead electricity prices with temporal hierarchy forecasting (THieF)](https://www.ml-quant.com/papers/arxiv/2508.11372/) (2025-08-20): The research introduces temporal hierarchy forecasting in predicting electricity prices, showing that reconciling forecasts for different time blocks improves accuracy at all levels. - [Deformation of semicircle law for correlated time series and Phase transition](https://www.ml-quant.com/papers/arxiv/2508.07192/) (2025-08-12): The study investigates the eigenvalue of the Wigner random matrix derived from a time series with temporal correlation, discussing the deformation of the semi-circle law and its moments of distribution and convergence. - [iQRA for Electricity Markets](https://www.ml-quant.com/papers/arxiv/2507.15079/) (2025-07-25): A new method, Isotonic Quantile Regression Averaging (iQRA), for generating probabilistic forecasts from point forecast ensembles in electricity markets, outperforms other methods in reliability and sharpness. - [Forecasting NYC Yellow Taxi Ridership Decline: A Time Series Analysis of Daily Passenger Counts (2017-2019)](https://www.ml-quant.com/papers/arxiv/2507.10588/) (2025-07-17): A study predicting daily passenger counts for New York City's yellow taxis from 2017-2019 shows a consistent decline in ridership, with the most accurate predictions made using a first-order autoregressive model. - [Efficiency through Evolution, A Darwinian Approach to Agent-Based Economic Forecast Modeling](https://www.ml-quant.com/papers/arxiv/2507.04074/) (2025-07-10): The article presents a new Darwinian Agent-Based Modeling method for macroeconomic forecasting, which uses evolutionary principles and simple rules to create realistic economic patterns efficiently. - [Temperature Sensitivity of Residential Energy Demand on the Global Scale: A Bayesian Partial Pooling Model](https://www.ml-quant.com/papers/arxiv/2506.22768/) (2025-07-03): A study found that global residential energy demand rises at temperatures below -5 degrees Celsius and above 30 degrees Celsius, with developed countries more sensitive to high temperatures.