Welcome to this week’s roundup of the latest research on investing and other valuable resources. Below, you’ll find a carefully curated list of highlights, with each title linking directly to its source for further reading. Thank you for reading and don’t forget to hit the like button.
Crypto
Bitcoin responds positively and significantly in the short term to Tether minting but shows no response to Tether burning. However, the effect is short-lived, lasting for 30-60 minutes.
How To Profitably Trade Bitcoin’s Overnight Sessions? (Vojtko and Cyril)
Bitcoin exhibits significant returns during overnight sessions, particularly on weekends and early weekdays, despite being traded 24/7. The paper proposes strategies exploiting this overnight effect and local price highs.
Equities
The Aggregated Equity Risk Premium (Azevedo, Riedersberger, and Velikov)
The authors use deep neural networks to predict individual stock returns using firm and macro features. Aggregating these forecasts and averaging across networks outperforms benchmarks in predicting market returns.
Social Media Sentiment and IPO Pricing (Xian)
More optimistic social media sentiment leads to higher IPO first-day returns but lower long-term returns.
Assessing Market Beta Estimates (Jylha, Liu, and Lof)
Model averaging across twelve different methods of measuring the market beta outperforms individual estimates in approximating the true market beta. Additionally, the Scholes-Williams beta demonstrates significantly better performance compared to the baseline OLS beta.
Machine Learning and Large Language Models
Caution Ahead: Numerical Reasoning and Look-ahead Bias in AI Models (Levy)
Large language models struggle with numerical reasoning in finance tasks and their apparent predictive ability often stems from look-ahead bias rather than genuine reasoning capabilities.
Follow the Leader: Enhancing Systematic Trend-Following Using Network Momentum (Li and Ferreira)
Network momentum models consistently outperform traditional trend-following strategies, yielding higher Sharpe ratios and improved skewness of returns.
Expected Option Returns and Large Language Models (Wang)
Large language models extract information effectively from news to predict delta-hedged option returns, outperforming simpler methods and which remain unexplained by standard risk factors.
TradingAgents: Multi-Agents LLM Financial Trading Framework (Xiao, Sun, Luo, and Wang)
The paper proposes a multi-agent framework of specialized analysts and traders powered by large language models. The framework processes a rich set of data, including price, news, and earnings data. It significantly outperforms benchmarks.
Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs (Drinkall, Pierrehumbert, and Zohren)
The paper compares traditional machine learning methods with large language models (LLMs) in predicting corporate credit rating changes, with a XGBoost model outperforming LLMs.
Macro
Estimating the Sign and Magnitude of the Inflation Risk Premium (Kim and Ronn)
The authors estimate the inflation risk premium and find it to be negative in most cases, with market-based measures like break-even inflation rates and inflation swap rates being lower than realized inflation or survey-based inflation expectations.
Good Inflation, Bad Inflation: Implications for Risky Asset Prices (Bonelli, Palazzo, and Yamarthy)
Inflation shocks predict returns on stocks and corporate bonds positively (negatively) when inflation is associated with higher (lower) economic growth.
Macro Tail Risk and Stock Returns (Chen, Li, Liu, and Tang)
Using economic surveys and partial least squares, the authors construct a macro tail risk measure that predicts stock returns out-of-sample.
Portfolio Management
The Importance of Diversification in Portfolio Protection Strategies (Horrex and Martinec)
This paper studies portfolio protection strategies, highlighting the need for diversification. It proposes a mix: 40% SPX rolling puts, 20% Trend, 20% Long Rates Vol, and 20% Quality, to manage the diverse intensity and length of equity drawdowns.
In-Sample and Out-of-Sample Sharpe Ratios for Linear Predictive Models (Jacquier, Muhle-Karbe, and Mulligan)
The authors analyze how much the in-sample performance of trading strategies based on linear predictive models is reduced out-of-sample due to overfitting. To mitigate overfitting, the paper emphasizes simplicity in modeling, focusing on a few strong signals over many weak ones, and using as much data as possible.
Volatility and Options
VIX1D with overnight weighting (Lee)
The paper proposes a new method to calculate the VIX1D index accounting for overnight market activity. This adjustment aims to fix a bias in the current calculation, which causes the index to drop significantly when markets open each day.
Combining Realized Volatility Estimators Based on Economic Performance (Skintzi and Fameliti)
This paper studies how to best combine forecasts of different volatility models. Rather than using statistical forecasting accuracy, the authors find improved performance by combining models based on their economic value.
Intraday Option Reversals: Return Predictability and Market Efficiency (Beckmeyer, Filippou, Zhou, and Zhou)
Ample research has identified intraday patterns in individual stocks. This paper finds significant intraday reversals for delta-hedged option returns, driven by demand pressures.
Blogs
Drawdown Implied Correlations Part 2: Generalized Downside Implied Correlations (CSSA)
Improving Industry Momentum with Sentiment Signals (QuantSeeker)
Piard’s Annual Seasonality (Allocate Smartly)
Refining ETF Asset Momentum Strategy (Quantpedia)
GitHub
pytimetk: Simplifying Time Series Analysis for Everyone
Medium
8 Volume Indicators You May Not Know (Kridtapon P.)
Got 7 Minutes? Use Python to Automate These 7 Tasks (Sharma)
Ten Predictions for Data Science and AI in 2025 (Widjaja)
Podcasts
The Hidden History of Eurodollars, Part 1: Cold War Origins (Odd Lots)
Practical Lessons from Warren Buffett | Timeless Wisdom from the Oracle of Omaha (Excess Returns)
From AQR Quant to Founder & CIO with Brian Hurst (Masters in Business)
Last Week’s Most Popular Links
Does Trend-Following Still Work on Stocks? (Zarattini, Pagani, and Wilcox)
The Day of the Week Effect (Vidal-Garcia and Vidal)
The Directionality of Earnings Surprises (Villanueva)
Disclaimer: This newsletter is for informational and educational purposes only and should not be construed as investment advice. The author does not endorse any specific securities or investments mentioned. While information is gathered from sources believed to be reliable, there is no guarantee of its accuracy, completeness, or correctness.
This content does not offer 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 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 are the author's own interpretations of the findings and content. These summaries should not be considered as definitive or comprehensive representations of the original works. Readers are encouraged to refer to the original sources for complete and authoritative information.
This newsletter contains 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 these external sites or for that of subsequent links. Users click on these links at their own risk.