Every week, I share a selection of interesting investment research drawn from academic studies, industry reports, and financial blogs, with links to the original sources for further reading.
Commodities
The Asymmetry of Basis Momentum in Commodity Futures (Jung and Uhl)
Studying 43 commodity futures markets, the authors find that most of the predictive power of basis momentum comes from the long side of the strategy. A long-only version of the strategy achieved a Sharpe ratio of 0.98, versus 0.60 for the conventional long-short approach. The asymmetry has weakened since 2010. A reminder that treating the long and short sides of a trading signal symmetrically may leave performance on the table.
Equities
Earnings-Announcement Reversals After 2011: A Reassessment (Crooker)
A well-documented earnings-announcement trading anomaly appears to have largely disappeared. Using US stock data from 1996–2024, the paper finds that earnings-specific short-term reversals declined from 0.73 percentage points in 1996–2011 to an insignificant −0.06 in 2012–2024. The decline survives multiple robustness checks.
Symbolic Regressions: Opening the Black Box of Equity Premium Predictions (Kuznetsov)
Can AI uncover stock market predictability without becoming a black box? Using US data from 1927–2021, the author finds that symbolic regression can discover interpretable nonlinear relationships and outperform traditional linear models in forecasting equity returns. Yet even the best model fails to beat the historical mean in out-of-sample forecast accuracy.
When Does Size Matter? (Azevedo, Brogaard, and Weibels)
Is the small-cap premium dead or just poorly timed? From 2005 to 2024, the Fama-French size factor (SMB) had a Sharpe ratio of −0.03. This paper finds that using machine learning to forecast individual stock returns and time SMB raises its Sharpe ratio to 0.61 (0.43 after estimated trading costs). A factor can have little unconditional return yet offer substantial opportunities when its expected return varies predictably over time.
Is the post-earnings-announcement drift still alive? The author studies US micro- and small-cap stocks (2015–2024) and finds that a long-only strategy returned 8.9% annually, rising to 12.3% when idle cash was invested in T-bills. However, most returns were attributed to market exposure, with only modest estimated alpha. Moreover, strategy capacity was limited.
Factor Investing
Factor Zoo Meets the News Library (Didisheim, Kelly, Pourmohammadi, and Tian)
AI can uncover investment factors that traditional financial data miss. This study identifies 228 interpretable factors from financial news. From 2016 to 2025, a news-based factor portfolio achieved an out-of-sample Sharpe ratio of 2.35, versus 1.54 for traditional factors (equal-weighted). The authors also find widespread market underreaction: 90 news factors exhibit significant return continuation, versus just 13 showing reversal.
Large Language Models
Agentic AI for Quantitative Investment Research: A Practitioner’s Guide (Mihov and Treleaven)
AI could make quantitative investment research dramatically faster. But will it produce better strategies or just more overfitted backtests? This paper reviews 62 agentic AI research systems. While many report promising results, rigorous out-of-sample testing often causes success rates to collapse. In at least two studies, no candidate survived. The authors argue that AI research needs deterministic backtesting, complete trial records, and independent evaluation. Automating research is not the same as automating alpha discovery.
Options
The 15:50 Candle: A Pre-Registered Study of an End-of-Day Signal in 0DTE SPX Options (Veldanda)
The 15:50 ET candle appears to predict the S&P 500’s closing move. When its body covers at least 60% of its range, it predicts the direction of the final nine minutes with 57.5% accuracy (2021–2026). Trading the signal using 0DTE SPX options earned an average of $67 per trade across 585 trades. However, the edge has weakened since 2023, and results are sensitive to trading costs and whether the signal is calculated using CFD, SPX, or SPY prices.
Portfolio Allocation
Total Portfolio Approach vs. Strategic Asset Allocation: Practical Routes to ‘Organisational Alpha’ (Scott)
Can maximizing the information ratio actually reduce portfolio efficiency? A new Schroders paper argues that benchmark-relative investing can produce suboptimal portfolios when active managers introduce unintended beta exposures or when alpha and beta are correlated. The proposed fixes? Tighter mandate constraints, tactical asset allocation, and more flexible risk budgets. Maximizing relative performance is not the same as maximizing risk-adjusted returns.
Blogs
Does Partial Risk Parity Improve Portfolio Diversification? (Quantseeker)
AI for systematic traders - this is the least stupid way to do it. (Rob Carver)
The Part Time Trader · Part 7: Thirty-Four Ways to Measure the Same Thing (The Algorithmic Advantage)
Is the Illiquidity Premium Really Gone? (Alpha Architect)
The Modified Gerber Statistic: A Threshold-free Co-Movement Statistic for Covariance Estimation and Portfolio Construction (Portfolio Optimizer)
Learning cross-asset macro investing (Macrosynergy)
Podcasts
Richard Falk-Wallace – Risk Models for the Front Office with Arcana (Flirting with Models)
30 Years of Trading Wisdom with from a $500 Million Fund Manager | Ross Haber (TraderLion)
I Was the Algorithm Before Algorithms Then I Had to Start Over · Scott Pulcini (Chat with Traders)
We Asked a Hedge Fund Manager With 40%+ Annual Returns Why Too Much Compute Could Break the AI Trade (Excess Returns)
Social Media & Industry Research
2027 US Outlook: The End of the Inflation Shocks (Goldman Sachs)
Understanding Return Expectations (Ilmanen and Maloney)
The smart money is selling equity (Owen Lamont, Acadian Asset Management)
Last Week’s Most Popular Links
Dynamic Strategy Selection (Cordoni, Sancetta, and Zhao)
The End-of-Day Reversal After 2019: A Pre-Registered Test on S&P 500 Stocks Excluding Heavily Traded Names (Vidovich and Zerjal)
Why optimising for the left tail of outcomes is like playing chess... (Rob Carver)
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.


