Weekly Research Recap
Latest research on investing and trading
Here’s your fresh weekly roundup of the most actionable investing insights from the last seven days, across academia, industry research, blogs, and social media, packed with direct links.
Equities
The Unpriced Risk in Momentum Strategies (Gao and Yuan)
Standard momentum is dominated by unpriced, time-varying factor risk. The authors address this issue by cross-sectionally regressing each stock’s 12-month momentum signal on Fama-French factor characteristics and ranking stocks on the residual. This “specific” momentum earns 1.14% per month with a Sharpe ratio of 1.05, versus 0.61 for raw momentum. Key takeaway: Momentum alpha lives in the factor-orthogonal residual.
Fiscal Uncertainty and Time-Varying Expected Market Returns (Yu, Xiao, Zhou, and Zhou)
Fiscal policy uncertainty (FPU) strongly predicts equity risk premia. Using U.S. data (1985–2024), the authors show FPU delivers out-of-sample R² of 1 to 4% across 1 to 12 months and surges to 17% at 12 months during high-FPU regimes. Economic gains appear only in these high-uncertainty states. Key takeaway: Fiscal uncertainty acts as a regime signal, with expected returns rising sharply when FPU spikes.
The decay of cay (Dauber and Lawrenz)
The consumption–wealth ratio (cay) has largely lost its predictive power: Today it shows near-zero quarterly R² and only 58 bp higher next-quarter excess returns per 1σ move, versus 220 bp historically. The decline reflects a breakdown in cointegration as asset wealth decoupled from aggregate consumption. A cay built on the top 10% households works better, but also fades. Key takeaway: Wealthy households’ consumption predicts returns better than aggregate consumption, but even this effect is shrinking.
Factor Models
Factor pricing across asset classes (Dang, Hollstein, and Prokopczuk)
The authors test 77 factors across seven asset classes and construct an integrated eight-factor model (U.S. market; international size, quality, and management; corporate bond carry and equity momentum; currency momentum; and equity index carry). It achieves out-of-sample Sharpe ratios above 0.8, over 50% higher than single-asset models, and when applied to 16,000 mutual funds, just 111 retain positive alpha. Key takeaway: Cross-asset factors explain most mutual fund returns, and most apparent “manager skill.”
Fixed Income
Interest Rate Surprises When the Fed Doesn’t Speak (Miranda-Agrippino and Williams)
Interest-rate expectations adjust just as predictably, and by similar magnitudes, after CPI or payroll releases as after FOMC announcements. At medium horizons, repricing is comparable: One-year rate surprises are about 5–8 bps across Fed and non-Fed events, and past payroll news significantly predicts these moves. Accounting for risk premia does not remove predictability. Key takeaway: “Policy surprises” largely reflect systematic macro-information updates, with Fed communication often serving as another transmission channel.
Macroeconomic Belief Distortions and Expected Returns in Treasury Bonds (Gong, Zhao, and Zhu)
Treasury returns are strongly influenced by systematic macro belief errors beyond what term-structure risk explains. A real-time macro factor captures biased growth and inflation expectations, delivering up to 33% out-of-sample R², with Sharpe ratios around 1.4. Predictability is strongest when disagreement is high. Key takeaway: Systematic errors in macro expectations are a powerful driver of expected bond returns.
Machine Learning and Large Language Models
Pairs Trading with Time-Series Deep Learning Models (Yilmaz and Sefer)
Transformers improve pairs trading by predicting the direction of factor-based residuals jointly across assets, replacing static mean-reversion rules. After transaction costs, iTransformer achieves 34% annualized returns with a Sharpe ratio of 1.94 on S&P 500 (vs 0.57 for classical relative value), and a crypto Sharpe of 2.2. Key takeaway: Cross-asset residual prediction, not simple mean reversion, drives superior, tradable alpha.
Disentangling the sources of cyber risk premia (Marechal and Monnet)
Using NLP on 10-K filings, the authors construct firm-level cyber risk scores orthogonal to standard characteristics. Stocks in the highest cyber-risk quintile outperform the lowest by 0.6% per month (about 7% annually), with a long–short Sharpe ratio of 0.68. Returns are not explained by conventional factors. Key takeaway: Cyber exposure behaves like a priced risk factor and deserves consideration in equity portfolio construction.
Insider Purchase Signals in Microcap Equities: Gradient Boosting Detection of Abnormal Returns (Zhao)
Using XGBoost on SEC Form 4 microcap purchases, the paper predicts the probability of stocks exceeding 10% abnormal return over 30 days following an insider buy. The dominant feature is distance from the 52-week high (36% of signal), followed by recent returns, volatility, liquidity, and insider traits. Buys disclosed after >10% run-ups deliver 6.3% abnormal returns. Key takeaway: In microcaps, insider alpha comes from buying into strength, not buying dips.
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining (Han et al.)
The paper introduces QuantaAlpha, an LLM-driven alpha discovery framework that treats research as an evolving system rather than one-shot prompt engineering. On CSI 300, it delivers 27.8% annualized excess return with just 8.0% max drawdown, and the learned signals transfer well to CSI 500 and S&P 500 (160% / 137% cumulative excess returns). Key takeaway: Alpha discovery as an evolving system, not one-shot prompts, builds more robust, regime-resilient signals.
Blogs
Point-in-time economics and financial market forecasting (Macrosynergy)
A Simple Intraday Signal That Predicts Next-Day Returns (QuantSeeker)
Pragmatic Asset Allocation Across Market Cycles (Quantpedia)
Three Risks of Relying on the S&P 500 in Retirement Planning (CFA Institute)
Podcasts
Lowest Cash Levels Ever | Kevin Muir on Why It’s Time to Buy Hedges (Excess Returns)
Trading Legend: His Strategy Has Made the MOST Millionaire Traders - StockBee (Words of Rizdom)
Biotech Just Had Its Big Reset - Here’s What Comes Next (Dan Rasmussen, D.A. Wallach & Meb Faber) (Meb Faber Show)
Social Media & Industry Research
The Long Volatility Premium: Short the Market, Get Paid? (Alpha Architect)
Understanding Implied Forwards (Kris Abdelmessih)
Everything Everywhere All at Once: Conglomerates and the Disappearing Diversification Discount (Research Affiliates)
Last Week’s Most Popular Links
Option Factor Momentum (Käfer, Mörke, and Wiest)
A Trend Following Deep Dive: The Optimal Market Mix for a Trend Follower (Man Group)
The Asset Allocation Wisdom of Wall Street (Mamaysky)
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.