Weekly Research Recap
Latest research on investing and trading
Hi there. It’s time for this week’s recap of top investing research, with direct links to the original sources for easy access. As mentioned last week, there won’t be a Thursday post this week as I’m away on holiday. Normal posting resumes next week.
Commodities
Political Uncertainty and Commodity Markets (Hou, Tang, Tao, and Zhang)
Commodity markets often respond sharply to political uncertainty, but the exact mechanism by which this happens hasn't been fully understood. This paper demonstrates that commodity prices tend to fall when political uncertainty arises in countries that consume a lot of commodities, such as the U.S. or Japan. In contrast, prices rise when political uncertainty hits major producers, like Brazil or Russia. For investors, the findings suggest that it may be possible to time commodity exposures based on upcoming elections in key countries.
Crypto
Microstructure and Market Dynamics in Crypto Markets (O’Hara, Easley, Yang, and Zhang)
Using 1-minute data for five major cryptocurrencies, the authors compute standard market microstructure measures such as liquidity and trade toxicity, and show that these metrics help predict short-term changes in return characteristics like volatility, autocorrelation, and skewness.
Equities
Fundamental Growth (Arnott, Brightman, Harvey, Nguyen, and Shakernia)
Rather than defining growth stocks based on high valuation ratios or other price-driven metrics, this paper argues for identifying growth through fundamental measures like revenue and profit growth. Building growth indices using these fundamentals, while avoiding price-based selection and weighting, delivers significant alpha relative to traditional growth indices.
Revisiting factor momentum: A one-month lag perspective (Rönkkö and Holmi)
While equity factors often exhibit momentum, recent studies suggest this may simply reflect a static tilt toward historically high-performing factors. This paper shows that momentum based on one-month returns delivers significant returns and alpha, even after controlling for such static exposures. Overall, the findings indicate that short-term factor momentum is a robust and pervasive feature of the data.
Assessing Asymmetry Risk Premium in U.S. Stock Markets (Liu, Chen, and Zhang)
Many investors are drawn to stocks with lottery-like upside, often leading to overpricing and eventual underperformance. This paper introduces a new way to measure such upside asymmetry using a distribution-based approach that captures the full shape of each stock’s return distribution. A simple long-short strategy, buying low-asymmetry stocks and shorting high-asymmetry ones, delivers strong, risk-adjusted returns (before costs). The key takeaway: Stocks with lottery-like characteristics tend to underperform on average.
Stock Splits are Not Dead: Implications of Reappearing Stock Splits (Chung, Li, and Liu)
The paper notes that the number of firms splitting their stocks has ticked higher in recent years. Even large-cap firms are increasingly using stock splits to draw attention from both investors and customers, leading to higher trading activity and stronger sales. These effects are especially pronounced among smaller and less institutionally owned firms, which benefit the most from the increased visibility.
Estimating stock mispricing (Zhang)
Many studies focus on short-term stock return anomalies, but long-term mispricing, how much prices deviate from intrinsic value, has been harder to measure. This paper introduces a new approach that uses a neural network and a large set of firm characteristics to predict five-year abnormal returns. The findings suggest that some stocks are significantly overpriced or underpriced, and these mispricings persist over time. A monthly rebalanced strategy that goes long undervalued stocks and short overvalued ones delivers significant alpha over the long run.
Using ETF Index Shares to Hedge Stock Market Risk Exposures (Flannery)
Many investors seek protection from market downturns, but traditional hedging tools like derivatives can be costly or complex. This paper shows that inverse ETFs, even those with modest leverage, offer a simpler way for retail investors to reduce market exposure. Although commonly criticized for multi-day use, the study finds they remain effective over longer periods, making them a practical, low-maintenance hedging tool.
Machine Learning and Large Language Models
Risk-Based Peer Networks and Return Predictability: Evidence from Textual Analysis on 10-K Filings (Yuan and Zhang)
Previous research shows that returns can be predicted using the past performance of peer firms. This paper applies topic modeling to the risk disclosure section of 10-K filings to identify firms with similar risk exposures. A long-short strategy based on their peers’ past one-month returns generates strong alpha. The effect is most pronounced among smaller, less-followed firms, consistent with information gradually making its way into prices.
Seemingly Virtuous Complexity in Return Prediction (Nagel)
This paper challenges the “virtue of complexity” in return prediction. While prior work claimed that overparameterized models trained on tiny samples can deliver strong out-of-sample performance, the author shows they effectively reduce to simple volatility-timed momentum strategies. The paper doesn’t reject complex models altogether, but questions their ability to truly learn when data is noisy and limited. This issue is exacerbated when predictors are persistent and correlated, as is often the case in finance (e.g., valuation ratios, accounting metrics, and macroeconomic variables).
Machine Learning for Financial Tail Risk Forecasting (Gupta)
This paper notes that many investors and institutions still rely on traditional, perhaps outdated, methods to predict tail risks. The author instead demonstrates that a LightGBM model offers superior performance in forecasting tail risks and volatility. The model is tested on electricity spot prices, which are shown to exhibit extreme volatility and heavy tails, as evidenced by large excess kurtosis.
Portfolio Optimization
skfolio: Portfolio Optimization in Python (Nicolini, Manzi, and Delatte)
This paper introduces skfolio, a Python library for portfolio optimization built on scikit-learn.
Blogs
PCA analysis of Futures returns for fun and profit (Rob Carver)
Weekly Research Insights - Using VIX to Time High-Beta Stocks (QuantSeeker)
GitHub
Hands On Large Language Models
Medium
Multi- Agents LLM Financial Trading Framework (Vashistha)
Podcasts
What Makes a Good Quant Researcher, with Gappy Paleologo (Money Stuff)
How You Get and Actually Keep a Job at a Multi-Strat Hedge Fund (Odd Lots)
Social Media
Expand Your Mind and Your Commodity Universe (Research Affiliates)
On The Rise of Passive Investing (Campbell Harvey)
My View On The Jane Street Story (Alexander Gerko)
Managed Futures Funds YTD (Tyler Lovingood)
Last Week’s Most Popular Links
Market Crash Risk and Return Predictability (Sun)
How to Maximize Momentum Returns in Foreign Exchange Markets? (Liu)
Predictable Currency Crashes (Sun, Wang, and Wang)
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.