Each Tuesday, I share a curated selection of the past week’s most interesting investment research and ideas, spanning academic studies, industry analysis, independent research, and discussions from across social media. Sources are linked throughout.
Equities
Noisy factors? The retroactive impact of methodological changes on the Fama–French factors (Akey, Robertson, and Simutin)
The authors show that historical Fama-French factor returns have changed across data vintages, partly because of revisions to the construction methodology. Those changes can materially alter estimated alphas, betas, and even the statistical significance of some anomalies. Key takeaway: For reproducible factor research, the data vintage matters.
Option Prices, Analyst Expectations, and Stock Returns (Martin, Rodenkirchen, Wagner, and Wang)
Using S&P 500 stocks from 1996 to 2025, the authors find that an option-implied expected-return measure predicts future returns from 1 to 12 months and substantially outperforms analyst price-target-based forecasts. At 12 months, it delivers a 21.3% out-of-sample R² relative to price-target forecasts. Key takeaway: Option prices contain information about expected returns that analyst forecasts largely miss.
Stale Data, Persistent Alpha (Fan and Li)
Accounting-based anomalies remain surprisingly strong even with stale information. Across 94 anomalies, median monthly CAPM alpha falls from 36 bps using the conventional 4-month data lag to 28 bps using year-old accounting data. Even at 2–3 year lags, substantial alpha remains. Key takeaway: Information releases explain part of anomaly returns, but much of the alpha persists long after the underlying information becomes public.
Hedge Funds
Hedge Fund Performance and Interest Rate Conditions: Evidence from Regulatory Data (Banegas)
Hedge funds are far from uniformly exposed to interest-rate risk. Using regulatory data on 4,883 hedge funds, the paper finds that higher Treasury volatility generally hurts returns, while a steeper yield curve helps. But the effects vary sharply across styles: A 100 bp steepening is associated with +1.75 pp monthly returns for equity funds, but lower returns for relative-value funds. Key takeaway: The same rate environment can produce very different outcomes across hedge fund strategies.
Machine Learning & Large Language Models
Fedspeak, LLM-Derived Signals, and High-Frequency Trading (Wei)
Using LLMs to measure shifts in tone and semantic content between FOMC statements and subsequent communications, this paper finds that new information, particularly in the minutes, is associated with significant intraday price movements across Treasuries, equities, and FX. Key takeaway: The initial FOMC statement does not contain the full policy signal; later communication can provide additional information that markets price.
Crowding in an Artificial World: AI and the Future of Investing (Chincarini, Falvey, and Moneta)
AI can make investing more crowded, not more diverse. Four independent AI agents received the same 209 published return signals and were asked to build long-short equity strategies. Their six distinct strategies ultimately relied on just five signals, producing highly correlated holdings, trades, and returns. Key takeaway: Independent AI investors can converge on remarkably similar strategies when working from the same set of published return signals.
Label alchemy: Target engineering for improved stock selection (Coqueret and Guida)
In ML for stock selection, the prediction target can matter more than the model. Using 1,960 U.S. stocks and 122 features, the authors keep the features and model fixed but change how forward returns are represented. Transforming returns into normalized cross-sectional ranks raises the long-short Sharpe from 0.68 to 1.69. Key takeaway: Improving the return target can be more valuable than building a more sophisticated model.
Options
The Common Source of Option Return Anomalies (Gerchik)
Most option return anomalies seem to be different versions of the same trade. Across 18 characteristics, the paper finds that about 80% of the average long-short return is explained by exposure to stocks with different implied volatility. Much of the effect is concentrated around the monthly expiration window. Key takeaway: Many known option anomalies largely reflect a common volatility-related effect around option expiration.
Portfolio Construction
Inference-Based Performance Evaluation Using the Sortino Ratio (Ledoit and Wolf)
The Sharpe ratio can penalize strategies for upside volatility and hide important differences in downside risk. This paper develops statistical inference for the Sortino ratio, allowing investors to test whether differences in downside-risk-adjusted performance are actually significant. Key takeaway: A higher estimated Sortino ratio is not enough; investors should ask whether the difference is statistically meaningful.
Don’t Fix Your Fixed Income Allocation (Lucas)
For long-horizon investors, bonds have historically been a substantial drag on returns. Using 155 years of U.S. data, the paper finds that all-equity portfolios beat 70/30 portfolios in 71% of 10-year periods, 90% of 30-year periods, and 95% of 40-year periods, though with larger drawdowns. Key takeaway: The longer the investment horizon, the weaker the historical case for a constant bond allocation.
Blogs
Macro demand factors and rates trading strategies (Macrosynergy)
Do Airline Stocks Take Off Around U.S. Holidays? (Quantpedia)
Tom Carlson’s Adaptive 60/40 Portfolio: Momentum-based Selection of Stock Diversifiers (Portfolio Optimizer)
Better Debt (John H. Cochrane)
Is Trend Still Your Friend? A Microstructural Explanation for the Demise of Short-Term Trend-Following (Alpha Architect)
Competition for Capital (Goldman Sachs)
Vanguard Capital Markets Model (Vanguard)
Podcasts
$242 Billion Investor on AI, Market Bubbles & How the Best Investors Build Portfolios (How I Invest)
RE-RELEASE: Texas Trend Following with Salem Abraham (RCM Alternatives)
Last Week’s Most Popular Links
Taking Carry Trading Seriously (Breedon and Vitale)
Intermediate-Term Reversal (Huang, Vincent, and Yeh)
Binary Bias and Stock Returns (Fattinger, Hanspal, Koval, and Steshkova)
Disclaimer: This newsletter is for informational and educational purposes only and should not be construed as investment advice. The author does not endorse or recommend any specific securities or investments. While information is gathered from sources believed to be reliable, there is no guarantee of its accuracy, completeness, or correctness.
This content does not constitute personalized financial, legal, or investment advice and may not be suitable for your individual circumstances. Investing carries risks, and past performance does not guarantee future results. The author and affiliates may hold positions in securities discussed, and these holdings may change at any time without prior notification.
The author is not affiliated with, sponsored by, or endorsed by any of the companies, organizations, or entities mentioned in this newsletter. Any references to specific companies or entities are for informational purposes only.
The brief summaries and descriptions of research papers and articles provided in this newsletter should not be considered definitive or comprehensive representations of the original works. Readers are encouraged to refer to the original sources for complete and authoritative information.
This newsletter may contain links to external websites and resources. The inclusion of these links does not imply endorsement of the content, products, services, or views expressed on these third-party sites. The author is not responsible for the accuracy, legality, or content of external sites or for that of any subsequent links. Users access these links at their own risk.
The author assumes no liability for losses or damages arising from the use of this content. By accessing, reading, or using this newsletter, you acknowledge and agree to the terms outlined in this disclaimer.
Paid subscriptions may not be available in all jurisdictions and may change without notice.