--- title: Asset Pricing & Factors url: https://www.ml-quant.com/topics/asset-pricing-factors/ 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 --- # Asset Pricing & Factors Factor models, anomalies, the cross-section of returns and what survives publication. 249 papers featured; 20 in the last 12 months. Papers featured per quarter: 2023 Q2 9, 2023 Q3 24, 2023 Q4 23, 2024 Q1 35, 2024 Q2 24, 2024 Q3 25, 2024 Q4 22, 2025 Q1 31, 2025 Q2 31, 2025 Q3 5, 2025 Q4 8, 2026 Q1 0, 2026 Q2 0, 2026 Q3 12 ## Most cited - [Bubble economics](https://www.ml-quant.com/papers/arxiv/2311.03638/): 43 citations. Nonstationary Phenomenon: The article discusses the theory of rational asset price bubbles, highlighting that bubbles linked to real assets like stocks and housing are nonstationary phenomena tied to unbalanced growth. - [NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks](https://www.ml-quant.com/papers/arxiv/2409.03024/): 24 citations. A Synthetic Mobility Dataset: The paper presents NUMOSIM, a synthetic mobility dataset for testing anomaly detection techniques, simulating realistic mobility scenarios and anomalies to improve geospatial mobility analysis. - [In Search of the True Greenium](https://www.ml-quant.com/papers/ssrn/4744608/): 20 citations. The study introduces a robust green score and expected returns to calculate the greenium, the expected return of green securities compared to brown, which is found to be more negative in greener countries and over time. - [Leverage, Endogenous Unbalanced Growth, and Asset Price Bubbles](https://www.ml-quant.com/papers/arxiv/2211.13100/): 10 citations. The paper introduces a new theoretical framework to understand asset price bubbles in dividend-paying assets, examining a macro-finance model with a positive feedback loop between capital investment and land price. - [HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE](https://www.ml-quant.com/papers/arxiv/2306.02848/): 8 citations. HireVAE is a deep learning-based model that outperforms previous methods in terms of active returns in stock market benchmarks. - [The Cross-Section of Factor Returns](https://www.ml-quant.com/papers/ssrn/4441376/): 7 citations. Most of the 150 equity factors examined show positive returns but fail to deliver excess returns after accounting for risk, especially in downturns. - [When can weak latent factors be statistically inferred?](https://www.ml-quant.com/papers/arxiv/2407.03616/): 7 citations. The article introduces a new theory for principal component analysis (PCA) under the weak factor model. This theory accounts for cross-sectional dependent components and provides finite-sample characterizations for estimation error and statistical inference uncertainty level, improving upon previous research. - [Exploratory Control with Tsallis Entropy for Latent Factor Models](https://www.ml-quant.com/papers/arxiv/2211.07622/): 7 citations. The research uses Tsallis Entropy in models with latent factors to optimally control and explore the state space, proving that the optimal state distribution is q-Gaussian, which can be used in creating robust statistical arbitrage trading strategies. - [Network Momentum across Asset Classes](https://www.ml-quant.com/papers/arxiv/2308.11294/): 6 citations. The article discusses network momentum, a trading signal from asset momentum spillover, and its use in a multi-asset investment strategy that yielded a 22% annual return from 2000 to 2022. - [Interpretable Machine Learning for Asset Pricing](https://www.ml-quant.com/papers/ssrn/4473746/): 5 citations. The paper utilizes deep neural networks to more accurately estimate equity risk premia over time, enhancing the interpretability of machine learning in economics. - [Design choices, machine learning, and the cross-section of stock returns](https://www.ml-quant.com/papers/ssrn/5031755/): 5 citations. The performance of machine learning models in predicting stock returns is greatly influenced by their design choices, with nonstandard errors in portfolio returns surpassing standard errors by 59%. - [Does Peer-Reviewed Research Help Predict Stock Returns?](https://www.ml-quant.com/papers/arxiv/2212.10317/): 5 citations. The research suggests that the predictability of cross-sectional return predictors decreases by half in post-sample scenarios, indicating that theory doesn't improve prediction and peer-review often misinterprets mispricing as risk. ## Latest - [Trust, Rule of Law, and the Size Premium: Evidence from a Meta-Analysis](https://www.ml-quant.com/papers/arxiv/2609.26212/) (2026-09-25): Meta-analysis of 1,613 size-premium estimates across 31 countries finds that stronger rule of law is associated with larger size premia, contrary to intuition. - [From D&I to D&I: European Capital Markets' Regime Shift from Diversity and Inclusion to Defence and Infrastructure](https://www.ml-quant.com/papers/ssrn/7477998/) (2026-09-25): European defence stocks repriced sharply starting November 2021, two to three months before Russia's invasion, delivering 26% alpha and reflecting release of ESG-exclusion constraints. - [Speculative Leverage and Factor Momentum](https://www.ml-quant.com/papers/ssrn/7512099/) (2026-09-25): Factor momentum strategies earn 49 basis points per month extra return following quarters of rapid margin-debt growth, a predictability that persists after publication and reflects limits to arbitrage correction. - [Firm-Specific Price Delay and Momentum](https://www.ml-quant.com/papers/ssrn/7518623/) (2026-09-25): Momentum profits concentrate among firms with high price delay, a measure of information friction, directly supporting theories that gradual information incorporation drives momentum. - [Crossing the Zero Lower Bound: Negative Interest Rates and Corporate Valuation](https://www.ml-quant.com/papers/ssrn/7512572/) (2026-09-25): Comparing firms across the ECB's 2014 negative rate adoption shows treated European firms had higher valuations but reduced leverage, suggesting cash-flow and discount-rate channels dominate tax-shield effects. - [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. - [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. - [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. - [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. - [Interpretable Machine Learning for Asset Pricing](https://www.ml-quant.com/papers/ssrn/4473746/) (2025-12-28): The paper utilizes deep neural networks to more accurately estimate equity risk premia over time, enhancing the interpretability of machine learning in economics. - [Asset Pricing and Stochastic Discount Factors](https://www.ml-quant.com/papers/ssrn/4465240/) (2025-12-28): The paper outlines the required conditions for modeling stock prices with characteristics-based factor portfolios, addressing covariate structure issues. - [The Cross-Section of Factor Returns](https://www.ml-quant.com/papers/ssrn/4441376/) (2025-12-19): Most of the 150 equity factors examined show positive returns but fail to deliver excess returns after accounting for risk, especially in downturns. - [Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model](https://www.ml-quant.com/papers/arxiv/2512.16251/) (2025-12-19): The Consensus-Bottleneck Asset Pricing Model uses a neural network to mimic analyst reasoning, showing how investor beliefs influence asset prices and enhancing long-term predictions for U.S. stocks. - [Are Penalty Shootouts Better Than a Coin Toss? Evidence From International Club Football in Europe](https://www.ml-quant.com/papers/arxiv/2510.17641/) (2025-10-27): Using UEFA penalty shootout data (2000–2025) we find outcomes are essentially random—no measurable advantage from kicking order, venue, momentum, or team 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. - [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. - [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. - [Optimal Investment and Consumption in a Stochastic Factor Model](https://www.ml-quant.com/papers/arxiv/2509.09452/) (2025-09-13): The article discusses optimal investment and consumption in an incomplete stochastic factor model, offering a comprehensive characterization of the problem's well-posedness and an efficient numerical algorithm for computing the value function. - [Rethinking Beta: A Causal Take on CAPM](https://www.ml-quant.com/papers/arxiv/2509.05760/) (2025-09-13): A study suggests the Capital Asset Pricing Model should be viewed as associational, not causal, with beta reflecting market capture of underlying drivers, and risk management should focus on declared causal paths instead of fixed factors. - [Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models](https://www.ml-quant.com/papers/arxiv/2508.19006/) (2025-08-29): The study finds that pretrained RNN attention models can effectively derive returns and hedge risks in asset pricing, even during extreme market conditions like the COVID-19 pandemic. - [Dynamic Asset Pricing with {\alpha}-MEU Model](https://www.ml-quant.com/papers/arxiv/2507.04093/) (2025-07-10): The study investigates a dynamic asset pricing problem, showing that an agent's perceived ambiguity or ambiguity-aversion can lower the risk-free rate and increase the stock price. - [Overparametrized models with posterior drift](https://www.ml-quant.com/papers/arxiv/2506.23619/) (2025-07-03): The research warns about the sensitivity of large linear machine learning models in predicting equity premiums, suggesting caution in their use. - [Common Task Framework](https://www.ml-quant.com/papers/ssrn/5242901/) (2025-06-25): The Common Task Framework (CTF) can enhance innovation, effort, and honesty in research, and could be used in financial economics to assess asset pricing models. - [FOMC Announcement Premiums](https://www.ml-quant.com/papers/ssrn/5237922/) (2025-06-25): Currency risk premiums fluctuate on U.S. FOMC announcement days, with currencies expecting a larger reduction in implied variance earning higher returns. - [Deep IV Factor Models](https://www.ml-quant.com/papers/ssrn/5283770/) (2025-06-11): The Deep Implied Volatility Factor Model, combining neural networks and linear regression, is proposed for estimating the daily Implied Volatility surface of individual stock options, improving performance around earnings announcements. - [AI Asset Pricing Impacts](https://www.ml-quant.com/papers/ssrn/5277572/) (2025-06-04): The article presents a model that examines the impact of AI on the economy, portfolio choices, and asset prices, suggesting that AI increases output growth and volatility and influences investor behavior. - [A FOMO-based Capital Asset Pricing Model](https://www.ml-quant.com/papers/ssrn/5276817/) (2025-06-04): The paper presents a Fear of Missing Out (FOMO) Capital Asset Pricing Model, suggesting that investors gain satisfaction from avoiding underperformance compared to their peers.