Weekly Research Recap
Latest research on investing and trading
Time for another batch of top-tier investing research. Below is a carefully curated list of great papers from last week, each linked to the original source for easy access.
If you’re enjoying these posts, a like or subscribe is always appreciated, thank you for your support!
Bonds
Book-to-Market, Mispricing, and the Cross Section of Corporate Bond Returns (Bartram, Grinblatt, and Nozawa)
Many investors rely on book-to-market ratios to guide stock selection, but their use in bond markets has been less explored. This paper shows that corporate bonds with high book-to-market ratios tend to deliver higher future returns, even after adjusting for credit risk, liquidity, and other characteristics. The effect appears driven by mispricing rather than risk. As a result, investors may benefit by tilting portfolios toward corporate bonds with high book-to-market ratios.
The Prediction Power of Short Sale: Evidence from Corporate Bond Market (Yang and Peng)
Short interest is known to predict stock returns, with heavily shorted stocks often underperforming. This paper finds a similar pattern in the corporate bond market using Markit data. Heavily shorted bonds, especially in the high-yield segment after the 2008 crisis, tend to deliver weaker future returns. Investors could benefit from underweighting these bonds and favoring those with lower short interest.
Commodities
Disruptions at Sea: Shipping Sentiment, Pirate Attacks, and Commodity Price (Jia)
Commodity prices are usually determined by supply and demand, but this paper shows that sentiment in the shipping industry also plays a key role. Using a preconstructed index based on shipping news, the author find that negative sentiment, often driven by events like pirate attacks, predicts lower commodity prices. The impact is especially strong in sectors such as energy and agriculture.
Crypto
Arbitrage in Perpetual Contracts (Dai, Li, and Yang)
This paper explores the mechanics of perpetual futures in crypto markets and highlights the widespread use of a clamping function that dampens small price deviations, preventing constant funding adjustments. The authors derive new no-arbitrage bounds that account for this mechanism and find that, once clamping is included, prices generally stay within the bounds, though brief violations do occur during periods of high volatility.
Equities
Mispricing Decomposition and Global Mispricing Index (Azevedo, Chen, Kaserer, and Muller)
Many markets display return patterns that can't be explained by standard risk factors. To better capture these inefficiencies, the authors develop a global mispricing index that quantifies how much of stock return variation stems from systematic mispricing. The index is higher in markets with short-sale constraints, poor accounting standards, and lower financial development. Interestingly, technical trading strategies tend to perform better in markets where this mispricing measure is high.
Can Dividend-Price Ratio Predict Stock Return? (Wang)
Investors may wonder if stock prices can be predicted using simple financial ratios. This paper shows that one of the oldest metrics, the dividend-price ratio, has some power in forecasting monthly returns on the S&P 500. Using nearly a century of data, the ratio performs well both in-sample and out-of-sample.
Optimizing Market Anomalies in China (Wang, Duan, and Guo)
The paper builds 146 anomaly-based portfolios from China’s stock market and applies several optimization methods to combine them into a single, more stable, and higher-performing strategy. Liquidity-related anomalies consistently receive the highest weights in the optimized portfolios.
Do U.S. Presidential Election Results Impact the Size Premium? (Caglayan, Celiker, and Tepe)
Small-cap stocks don’t always outperform, and some say the size effect is dead. But this paper finds that small stocks beat large ones by a wide margin in the year after a Democrat wins the U.S. presidency, especially when replacing a Republican. The effect remains strong even after removing January returns and controlling for market cycles.
Machine Learning and Large Language Models
Interpretable Machine Learning for Macro Alpha: A News Sentiment Case Study (Zhang)
Markets often react quickly to news, but extracting useful trading signals from global headlines can be challenging. This paper assigns sentiment scores to global macro news using FinBERT and predicts daily returns on currencies and Treasury futures using machine learning. The model achieves high risk-adjusted returns, and among important features can be found sentiment dispersion, article impact, and recent shifts in news tone.
Machine Learning in GDP Nowcasting: From Lagging Indicators to Leading Algorithms (Kislitskiy, Marinchenko, and Veremiienko)
Official GDP figures arrive with a delay, making it hard for investors and policymakers to understand the current state of the economy in real-time. This paper tests whether machine learning models can improve GDP nowcasting compared to traditional methods. It finds that during stable periods, simple models work fine, but in volatile times, machine learning models provide more accurate and timely GDP forecasts.
Estimating Stock Market Betas via Machine Learning (Drobetz, Hollstein, Otto, and Prokopczuk)
Beta is a common way to measure a stock’s market risk, but can be difficult to estimate because it changes over time. This paper finds that machine learning models, especially random forests, generate more accurate and stable forecasts than traditional approaches. They perform especially well during market stress and for stocks that are typically harder to model, such as small caps and illiquid names.
Machine learning approach to stock price crash risk (Karasan, Alp, and Weber)
When investors grow too optimistic, stock prices can surge while hidden risks build up. Using a machine learning approach, the authors predict future stock price crashes more effectively than traditional methods. They also find that firm-specific investor sentiment is a strong warning signal: High sentiment often comes before a crash. Investors should be cautious when sentiment around a stock becomes overly positive.
Simulating Macroeconomic Expectations using LLM Agents (Lin, Sun, and Yan)
Many economic decisions rely on expectations about the future, yet it's still unclear how those expectations are formed. Traditional survey methods can be costly and limited in scope. This paper shows that large language model agents can simulate how households and experts form expectations about inflation and unemployment. The simulations reveal that personal history and prior beliefs account for much of the variation.
Real Estate
REIT Factors (Letdin, Seagraves, and Sirmans)
Many investors apply traditional equity factor models to REITs, but these vehicles have unique characteristics that such models may overlook. This paper builds six tailored REIT factors in the forms of size, value, momentum, quality, low volatility, and short-term reversal, and shows that most outperform standard equity factors. Momentum, quality, and reversal deliver particularly strong returns, even after transaction costs.
Risk Management
Tail Risk Hedging: The Superiority of the Naïve Hedging Strategy (Cao and Conlon)
Many firms use complex models to hedge against large market drops, but these approaches often rely on estimates that are difficult to get right. This paper shows that a simple rule, fully hedging each position with one matching futures contract, often performs better than more advanced models across various markets. It works particularly well during economic downturns. The findings suggest that simple, fixed hedging can be more effective in practice than complex strategies.
Blogs
Macro-aware risk parity (Macrosynergy)
Market Timing with Macro Surveys (QuantSeeker)
Cliff Smith’s BKLN Strategy (Allocate Smartly)
FinTwit and LinkedIn
Interview with Rob Arnott (Research Affiliates)
Meb Faber: The Bull Market In Diversification (Michael A. Gayed)
Bill Ackman on the Decline of Harvard (@BoringBiz_)
GitHub
Python for Finance (2nd ed., O'Reilly) - All Python code for the book Python for Finance
qlib - Quant investment platform
llm-course - Course covering Large Language Models
Medium
Still using the ‘You are an expert… ’ AI prompt Part 3 (Mehta)
Adaptive Momentum Investing: Leveraging Volatility Regimes for Enhanced Returns. (Filip)
Podcasts
Pavel Kycek - Generating Insane Returns with Quant Crypto Trading (The Algorithmic Advantage)
Betting on Chaos (Risk of Ruin)
Exploring Dual Momentum with Gary Antonacci (Fill The Gap)
AQR's Cliff Asness: Why Most Investors Quit Before Winning (David Weisburd)
Last Week’s Most Popular Links
Factor Investing Lecture 1: Intro to Factor Investing (Shi)
Short-Term Basis Reversal (Rossi, Zhang, and Zhu)
The short-duration premium and news announcements (Beckmeyer and Meyerhof)
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.