Weekly Research Recap
Latest research on investing and trading
This week’s recap curates the top investing insights from academic research, industry research, blogs, and social media, all sourced and linked.
Equities
Bottom-Up Capacity Constraints and the Limits of Anomaly Profitability (Cartea, Cucuringu, Jin, and Zhu)
Most stock anomalies fail when scaled. A capacity model tied to each stock’s tradable volume shows that over 70% of anomalies earn under $1,000/day OOS, and Sharpe ratios drop 35–45% once liquidity limits are applied. Only 20 of 128 predictors remain statistically significant before trading costs. Key takeaway: Predictability isn’t profitability; liquidity is the real constraint.
The decay of cay (Dauber and Lawrenz)
The consumption–wealth ratio (cay), the deviation from the long-run equilibrium linking consumption, income, and wealth, has lost most of its predictive power over the past two decades because asset wealth no longer tracks aggregate consumption and income. Yet a cay measure built from the top 10% wealthiest households still predicts market returns. Key takeaway: Cay’s signal now resides with wealthy households, whose consumption still tracks their asset wealth.
Retail Investor Horizon and Earnings Announcements (Vamossy)
Retail investors’ investment horizons, measured from StockTwits users’ self-reported holding periods, strongly predict earnings-related return patterns. Stocks followed by long-horizon investors show substantially larger post-announcement drifts. A horizon-based long–short strategy earns roughly 0.43% monthly alpha (before costs). Key takeaway: Retail investor horizons create persistent, tradable mispricing around earnings.
Forecast-Agnostic Portfolios (Guo and Wachter)
The paper shows that simple, volatility-targeted trades, sizing positions from a predictor’s demeaned value and choosing long or short only from the sign of its predictive coefficient, generate meaningful alpha. Yet these same predictors produce negative out-of-sample R² because predicting return magnitudes is far noisier than getting the direction right. Key takeaway: Predictors don’t need precise return forecasts to be useful; what matters is getting the direction right.
Investing
The Best Defensive Strategies: Two Centuries of Evidence (Baltussen, Martens, and van der Linden)
Across 222 years of data, low-risk, quality, and value provide steady downside protection, but multi-asset approaches are stronger. DAR4020, a long/short portfolio that goes long factors negatively correlated with 60/40 and shorts those positively correlated, delivers +1.0% in the worst 10% of months, while trend-following adds roughly 0.5%. Gold and puts fail long-run tests. Key takeaway: Combining DAR-style correlation hedges with trend-following offers the most robust defense.
The Quest for Neutrality in Asset Allocation (Al-Thani et al.)
The paper evaluates six risk-based allocation rules and finds that all outperform the ACWI benchmark on a risk-adjusted basis. Conviction Parity (CP), which equalizes each asset’s residual (unexplained) risk, stands out, delivering about 6.9% returns, low tracking error, and the highest information ratio (0.42). Key takeaway: Equalizing residual risk, not capital or volatility, produces the most stable portfolios.
Machine Learning and Large Language Models
Agentic Artificial Intelligence in Finance: A Comprehensive Survey (Aldridge et al.)
This is a comprehensive survey paper on agentic AI in finance, synthesizing prior research and outlining use cases across trading, portfolio management, and risk management.
A machine learning approach to risk based asset allocation in portfolio optimization (Agal, Raulji, and Odedra)
The paper presents a machine-learning risk-allocation framework that dynamically adjusts risk budgets using LSTMs and a data-driven regime detection model. In out-of-sample tests (2017–2022), it delivers a 1.38 Sharpe ratio, substantially outperforming risk parity and deep-learning benchmarks while significantly cutting maximum drawdowns. Key takeaway: Regime-aware, adaptive risk budgeting improves portfolio resilience, especially during volatile periods.
Options
Flipping the Arbitrage: How Option Prices Imply Negative Interest Rates (Chance and Zhang)
Across millions of SPX options over 27 years, box-spread prices almost always exceed their certain payoff because bid–ask spreads are exceptionally wide, generating average losses of −33% for SPX and −45% for NDX, and violating the time value of money, even when trading at midpoints. Investors effectively forfeit over $10.3 billion annually. Key takeaway: Wide bid–ask spreads force traders to overpay, embedding negative implied interest rates into index option prices.
Volatility
A GARCH model with two volatility components and two driving factors (Ballestra, D’Innocenzo, and Tezza)
The authors develop a two-factor GARCH model with spillovers and distinct leverage channels. Using S&P 500 data, it delivers a substantially better in-sample fit than one-factor benchmarks and improves both VaR forecasting and option-pricing accuracy out-of-sample. Key takeaway: Volatility is multi-dimensional; modeling separate volatility drivers improves risk forecasts and option valuation.
Blogs
Systematic stock selection with macro factors (Macrosynergy)
Systematic Edges in Prediction Markets (Quantpedia)
Which Sectors Move the Market on Fed Days? (Quantseeker)
GitHub
TradingAgents: Multi-Agents LLM Financial Trading Framework
Podcasts
Antti Ilmanen, how investors form long-run return expectations (Bogleheads)
The Man Who Cracked The Market Algorithm - Samir Varma PhD (Titans of Tomorrow)
You’re Missing the Most Important Lesson | 50 Great Investors Share the One Thing They’d Teach You (Excess Returns)
Re-run: Gappy Paleologo (Money Stuff)
Social Media & Industry Research
Hold the Dip (AQR)
Is It Too Late to Buy Gold? (Alpha Architect)
Active Extension: A Potential Solution for Improving Equity Returns (AQR)
Reads You May Have Missed (Man Group)
Last Week’s Most Popular Links
The Intra-Day Stock Return Periodicity Puzzle (Haendler, Heston, Korajczyk, and Sadka)
The factor games: May the p values be ever in your favor (Stellet and Moraes)
Day Trader Turned $3000 Into $2.1Million Using Data & Statistics (Words of Rizdom)
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.