Weekly Research Recap
Latest research on investing and trading
This week’s Tuesday Roundup features the most valuable investing insights I came across over the last seven days, spanning new academic and industry research, as well as high-quality blog posts. Links are included throughout for further reading.
Equities
Lost in the Multiverse: Methodological Uncertainty in Studying Global Equity Returns (Cakici, Fieberg, Neszveda, Piljak, and Zaremba)
Most country-level investing “anomalies” may be less robust than they appear. This paper shows that signals like momentum, beta, and idiosyncratic risk often fail to remain robust across alternative research designs. The most reliable predictors were market size, dividend yield, sovereign risk, and short-term momentum. Key takeaway: Always ask whether an investing edge survives different implementations.
Does Momentum Time Risk Rather Than Returns? (Zakamulin)
This paper challenges the standard view of time-series equity momentum. In the U.S. equity market, its edge comes primarily from identifying future volatility rather than predicting future returns. Long-only momentum improves risk-adjusted performance largely by avoiding high-volatility regimes, not by forecasting higher returns. Key takeaway: For equity momentum, risk timing matters more than return timing.
Liquidity Premium and Investment Horizons (Aldridge)
Not all trading volume is equally informative. Signed order flow is shown to predict the cross-section of next month’s stock returns, while raw volume adds far less information. Key takeaway: Net buying and selling carry more information than raw trading volume.
Options
Hearing and Seeing the Fed: Multimodal Signals Beyond Text in Intraday Option Markets (Filippou, Zhao, Zhou, and Zhou)
Markets don’t just react to what the Fed says; they react to how it’s said. Jerome Powell’s tone of voice and facial expressions are shown to contain incremental information beyond the transcript. Those multimodal signals improved intraday return forecasts and generated profitable 0DTE option trades even after full bid-ask spreads. Key takeaway: How the Fed communicates matters alongside what it communicates.
Portfolio Construction
Bond Portfolio Optimization (Ben Slimane, Cherief, Roncalli, and Xu)
Most portfolio optimization assumes historical risk is informative about future risk. The authors argue this assumption breaks down for individual bonds. As bonds age, duration falls, and credit risk evolves, making historical covariance matrices progressively less informative. Key takeaway: Fixed income requires dynamic risk models, not equity models with different inputs.
Hidden Factors in Portfolio Risk Models: A Finite-Sample Approach to Residual PCA (Kolm and Ritter)
The paper argues that residual PCA is a sensible way to search for missing risk factors, but the resulting factor should only be used if it is strong enough to be distinguished from estimation noise and its estimated loading direction can be reliably recovered. Key takeaway: Validate residual PCA factors before incorporating them into portfolio construction.
Prediction Markets
Settlement Manipulation in Prediction Markets (Dai, Jia, and Yu)
Prediction markets are often praised for improving price discovery. This paper argues that Polymarket's 5-minute Bitcoin prediction market can do the opposite. The authors show that it creates incentives to manipulate the underlying into settlement, degrading price discovery and transferring wealth from retail traders to manipulators. Key takeaway: Ultra-short asset-price prediction markets can create incentives that distort the underlying market rather than improve price discovery.
Trend Following
Is Trend Still Your Friend?: A Microstructural Account of the Demise of Short-Term Trend-Following (Kurth, Eisler, Rej, Bouchaud)
Why did short-term trend following stop working after 2009? This paper argues that the culprit wasn't overcrowding or capacity constraints. Instead, fast trend largely disappeared in small-tick futures contracts, while remaining surprisingly resilient in large-tick contracts, consistent with HFT-driven changes in market microstructure. Key takeaway: The viability of fast trend following depends on contract microstructure, not just the signal itself.
Blogs
Volatility Indicators for Predicting S&P 500 Drawdowns (Quantseeker)
Jumping back in the pool(ing): testing pooling by asset class and portfolio weight distance (Rob Carver)
Silicon vs. Satoshi: Tactical Asset Rotation Between NASDAQ-100 and Bitcoin (Quantpedia)
Podcasts
Ben Wellington – Complex Feature Engineering at Two Sigma (Flirting with Models)
The Bridge Ep. 11: Expensive Isn't a Bubble (iCapital, featuring Cliff Asness)
Ex-Two Sigma Quant: Why You Should Bet Against Conviction (Odds on Open)
Social Media & Industry Research
Learning to Replicate Expert Judgment in Financial Tasks (Mira Murati, Thinking Machines)
When Fear Spikes, Should You Buy? (Victor Haghani, Elm Wealth)
From Energy to Metals: Why to Still Diversify Into Commodities (Goldman Sachs)
The Disappearing Overnight Drift (Boyarchenko, Larsen, and Whelan; New York Fed)
Cruel Summer for Fixed Income (Citadel)
Last Week’s Most Popular Links
Skewness Managed Portfolios (Gong, Lynch, and Ogden)
Oil–VIX States as Conditional Signals for Cross-Asset Allocation (Aylsworth, Poechhacker, Schwaiger, and Werbach)
Systematic FX trading with regression learning and transaction cost analysis (Macrosynergy)
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.
Paid subscriptions may not be available in all jurisdictions and may change without notice.