This weekly roundup brings together a selection of noteworthy investment research from the past week, covering academic studies, practitioner insights, and investment blogs. Links to the original sources are included for readers who wish to explore the findings further.
Commodities
Weak Factors for Commodity Futures Portfolios (Nakagawa and Sakemoto)
What explains risk premia in commodity futures? Examining 38 commodities, the authors find that market-based uncertainty measures, including VIX, credit spreads, and financial conditions, are significantly priced. In contrast, news-based measures of geopolitical risk and policy uncertainty carry no significant risk premia. Financial market conditions appear more relevant for commodity risk pricing than geopolitical headlines.
Crypto
Are Cryptocurrency Factors Investable? Reassessing Liu, Tsyvinski, and Wu (2022) (Han)
Revisiting established crypto factors using data through May 2026, this paper finds that several long-short portfolios would have been liquidated despite statistically significant average returns. Even surviving momentum strategies experience drawdowns of 74–93%. Short-term momentum holds up best out of sample, while size, price, volume, and volatility premiums lose statistical significance.
Equities
Factor Timing with Transaction Costs (Gunturu and Lalwani)
Can factor timing outperform equal weighting after transaction costs? Using 50 long-short equity factors, the authors find that annually adjusting factor weights based on past returns and covariances improves risk-adjusted performance. Over 2000–2020, the strategy achieves a Sharpe ratio of 0.61 versus 0.45 for equal weighting, after trading costs.
Lever Up Your IRA: Understanding the Long Run Performance of Leveraged ETFs (Lai and Reilly)
Leveraged equity ETFs can be attractive investments even for long-term buy-and-hold investors. Examining 191 funds, financing costs and index autocorrelation are found to matter more for expected returns than volatility alone. In a lifecycle portfolio model, optimal allocations to leveraged equity ETFs range from 35% to 100%, challenging conventional investment advice.
Do Words Matter for Wall Street? Presidential Speech and the Stock Market (Bonaparte)
Do presidential speeches move the stock market? Analyzing nearly 16,000 presidential statements from 1993–2024, absolute S&P 500 returns are found to be 75% larger than usual the day after State of the Union addresses. Unscheduled national addresses increase overnight moves by 56%. Yet speech tone and other textual measures fail to predict return direction. Presidential addresses appear to be volatility events, not directional trading signals.
Stale Data, Persistent Alpha (Fan and Li)
Stock market anomalies remain profitable even with outdated information. Examining 94 accounting-based factors, median monthly CAPM alpha declines from 36 bps using four-month-old data to 28 bps using year-old data. Even three-year-old data retains 19 bps. Much of anomaly alpha appears linked to persistent firm characteristics rather than short-lived reactions to new information.
Revisiting Momentum Crashes: Volatility Timing across Developed and Emerging Markets (Feng, Huang, and Su)
Momentum crashes often occur when markets rebound after prolonged declines. Using international equity factor data through April 2026, the authors find that volatility scaling raises the momentum Sharpe ratio from 0.53 to 0.87 in developed markets and reduces maximum drawdown from 44% to 11%. However, improvements are considerably smaller after 2010, particularly in emerging markets.
Machine Learning & Large Language Models
Reading the News Without Hindsight: NoLBERT Topics and the Cross-Section of Stock Returns (Foley, Hartadi, Prakash, Takkallapalli, and Vatsal)
Can AI extract profitable trading signals from financial news? Analyzing 1.26 million articles and 1,000 US stocks, this paper finds that measuring news attention shocks relative to the past 63 days improves return forecasts compared with a 5-day window. Combining multiple models achieves a net Sharpe of 1.12, but does not significantly outperform price-only strategies. Selecting the best model in validation leads to losses out of sample.
Trading Costs and Machine-Learning Return Forecasts (Bianchi and Jiao)
Better stock return forecasts don’t necessarily mean higher profits. This paper finds that machine-learning models predict returns best among illiquid stocks, where trading costs are highest. For a $500M portfolio, weighting positions by liquidity and avoiding trades with insufficient expected returns raises the net Sharpe ratio from −0.38 to 0.42. The largest gains come from reducing trading costs, not improving forecasts.
Regime-Aware Interpretable Ranking for Sector Rotation (Koa et al.)
Can AI improve sector rotation? Using S&P 500 sector data from 2002–2024, researchers find that a regime-aware model improves sector ranking accuracy. Technical signals, particularly volume and volatility, dominate fundamentals, while signal persistence and cross-sector relationships are especially important. Interestingly, simple 12-month momentum performs worse than random at predicting future risk-adjusted sector rankings.
Blogs
Which Trend Indicator Works Best for Sector Rotation? (Quantseeker)
Diversification All the Way Down (Alpha Architect)
Less Wrong (Quantitativo)
Gary Antonacci: From Dual Momentum to Advanced Models (Concretum Group)
Podcasts
What $450M Portfolio Manager Learned From Paul Tudor Jones · Andrew Perry (Chat with Traders)
Hedge Fund Manager Joseph Walsh: Always Play Weaker Players (Odds on Open)
Why Trend Following Rewards Patience ft. Katy Kaminski (Top Traders Unplugged)
Social Media & Industry Research
The crash that wasn’t (Owen Lamont, Acadian Asset Management)
Quant Insight: Has the Alpha in Value and Momentum Decayed? (Guido Baltussen)
Last Week’s Most Popular Links
Convexity You Can Afford (Yoav Git)
Buying Duration: Index Rebalancing and Price Pressure in Government Bond Markets (Martinetti, Soebhag, and Verwijmeren)
Bespoke Realized Correlations for Multivariate Volatility Prediction (Kotehne and Patton)
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.