Weekly Research Recap
Latest research on investing and trading
Hi there. It's time for this week’s research recap, highlighting top investing insights from the past week with direct links to the full sources.
Commodities
News Sentiment and Commodity Futures Investing (Yeguang, El-Jahel, and Vu)
While momentum and carry strategies are well-known in commodities, this paper shows that weekly news sentiment from financial media also predicts returns. Using Refinitiv’s MarketPsych indices, the authors construct long-short portfolios that deliver strong risk-adjusted returns, even after accounting for costs. Combining sentiment with other signals further boosts performance. Overall, the paper suggests that news sentiment offers valuable short-term signals for commodity trading strategies.
Crypto
Stablecoins: Fundamentals, Emerging Issues, and Open Challenges (Mahrous, Caprolu, and Di Pietro)
This comprehensive survey paper provides structure to the fragmented research on stablecoins by reviewing over 200 studies that span economics, technology, and regulation. While stablecoins often serve as safe havens and are gaining real-world adoption, the paper highlights major gaps in understanding their risks and long-term implications.
A Trend Factor for the Cross Section of Cryptocurrency Returns (Fieberg, Liedtke, Poddig, Walker, and Zaremba)
As fundamental data is often scarce in crypto, investors tend to rely on price and volume patterns. This paper introduces CTREND, a trend signal that combines over two dozen technical indicators using elastic net to forecast returns. CTREND consistently beats other strategies, even after adjusting for risk and costs. Investors can possibly use it to build more effective trend-following strategies, including in large and liquid cryptocurrencies.
Decrypting Crypto: How to Estimate International Stablecoin Flows (Reuter)
Tracking cross-border crypto activity can be challenging due to the pseudonymous nature of blockchain. This paper addresses that problem by creating a method to estimate where stablecoin transactions are coming from and going to. By combining AI, domain name analysis, and machine learning trained on wallet behavior, the author finds that stablecoin use is highest in emerging markets relative to GDP and surges when local currencies weaken. Overall, the paper highlights how crypto flows respond to global dollar demand and offers new tools for tracking capital movement.
Fixed Income
The Impact of Debt and Deficits on Long-Term Interest Rates in the US (Furceri, Goncalves, and Li)
For decades, rising U.S. debt and deficits haven’t seemed to push up long-term interest rates, leading some to question whether fiscal policy still matters for borrowing costs. This paper shows that the link is real but time-varying: During periods of low deficits, the effect was muted, but it has grown stronger as fiscal conditions have worsened. Investors should expect higher projected debt and deficits to gradually raise long-term rates and financing costs.
Machine Learning and Large Language Models
Forecasting Intraday Volume in Equity Markets with Machine Learning (Cucuringu, Li, and Zhang)
While many papers focus on forecasting intraday returns, this study predicts intraday trading volume. Using 15-minute intervals for U.S. stocks, the authors evaluate a range of models and find that non-linear approaches deliver strong predictive accuracy. These forecasts are then applied to improve VWAP execution and increase the fill rate of passive limit orders.
AI Challenges in Mathematical Investing (Lopez de Prado)
Most AI tools are designed for prediction, but investing requires more than just forecasting. This paper explains that successful investment decisions hinge on understanding cause and effect, not just identifying patterns. Challenges like non-stationarity, weak signals, and small datasets make this especially hard. As a result, investors should be cautious with AI models that don't explain why something works, and instead focus on causal reasoning and robust testing.
Eroding and Non-Scalable CNN Signals: A Replication and Extension (Kaczmarek and Pukthuanthong)
Several studies have highlighted the potential of Convolutional Neural Networks to forecast stock returns using price chart images. This paper shows that while early results were impressive, the predictive power of these models has steadily eroded. Models trained on newer data perform worse, and any remaining signal is confined to small and illiquid stocks.
Risk Management
A Safe Haven Index (Baur, Dimpfl, and Pena)
During market crashes, investors often seek refuge in assets like gold, government bonds, or currencies such as the Swiss franc and Japanese yen. While prior research tends to examine these assets separately, this paper builds a Safe Haven Index (SHI) using the first principal component of returns. The index reliably spikes during crises, offering a broader gauge of market stress.
Valuation
Firm Valuation in Practice: A Case Study Analysis of DCF Valuation (Scariati, Dal Mas, and Ceka)
Many investors use DCF models to value companies, and this paper offers a detailed discussion on how the method works and what assumptions it relies on. The authors show that small changes in growth rates, discount rates, or cash flow forecasts can significantly alter valuation outcomes. Using a real-world case, they highlight both the strengths and limitations of the model, emphasizing that DCF models should guide structured thinking rather than serve as a precise prediction tool.
Blogs
Weekly Research Insights - A Simple and Effective Tactical Allocation Strategy (QuantSeeker)
Don’t Just Trend It, Curve It (Twoquants - Moritz Heiden)
When your strategy works, is it just dumb luck? How to stack the odds in your favour (Robot Wealth)
GitHub
AI Agents for Beginner - 11 Lessons to Get Started Building AI Agents
Finance - 150+ quantitative finance Python programs
Podcasts
Ep. 1348: Jerry Parker, Moritz Seibert, Richard Liddle and Gareth Abbot (Michael Covel Trend Following)
The Lie Your Stock's Price is Telling You | Kris Abdelmessih on Why Options Hold the Truth (Excess Returns)
RenMac's Head of Economics Neil Dutta on Recession Indicators (Masters in Business)
Social Media
From black box to glass box: Understanding and attributing machine learning models (Matthias Hanauer, Robeco)
While markets often crash, they’re never crashing (Owen A. Lamont, Acadian)
Understanding return expectations, Part 5 (AQR)
Last Week’s Most Popular Links
Data-mined Anomalies and the Expected Market Return (Li, Platanakis, Ye, and Zhou)
In-Sample and Out-of-Sample Sharpe Ratios for Linear Predictive Models (Jacquier, Muhle-Karbe, and Mulligan)
Thematic Investing: A Risk-based Perspective (Candes, Hastie, Hogan, Kahn, Luo, and Spector)
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.