Can machine learning models better predict stock returns if they are tailored to specific industries, or is a one-size-fits-all (generalist) approach sufficient? This question lies at the heart of a recent research paper by Matthias Hanauer, Amar Soebhag, Marc Stam, and Tobias Hoogteijling. Their findings suggest that the optimal solution lies somewhere in between: a “Hybrid” machine learning model that is aware of industry structures but still trained on the full cross-section of stocks offers the best performance.

With financial markets increasingly whipsawed by geopolitical tensions and unpredictable policy shifts from the Trump administration—investors are once again questioning how to understand risk, fear, and the true drivers of returns. A recent and compelling paper dives into this debate with a provocative thesis: in “Fear, Not Risk, Explains Asset Pricing,” authors Rob Arnott and Edward McQuarrie argue that traditional models built on quantifiable risk have failed to explain real-world returns, and that fear—messy, emotional, and deeply human—is the missing piece.

The recent imposition of sweeping global tariffs by President Donald Trump has triggered a sharp and sudden selloff across global equity markets. In times like these, it’s natural for panic to set in. However, as quantitative investors, our strength lies in data-driven decision-making, risk management, and maintaining discipline when others lose theirs.

Rather than reacting emotionally, the prudent course of action is to reassess the robustness of our portfolios. Are we diversified across uncorrelated strategies? Do we have components in place that act as hedges during market crises? Fortunately, the tools provided by Quantpedia can help investors, traders, and portfolio managers identify, test, and deploy crisis-resilient strategies in a structured and evidence-based manner.

The dominance of mega-tech stocks, particularly the “Magnificent 7,” in both U.S. and global equity indexes has a profound impact on factor portfolios. When constructing value-weighted smart beta strategies, these portfolios often end up heavily concentrated in a few individual stocks. This concentration introduces idiosyncratic risk, skewing the risk profiles of factor strategies. While no active strategy can entirely avoid the influence of these high-market-cap stocks, it is critical to limit their exposure to reduce idiosyncratic risk and improve the stability of factor-based approaches.

The growing urgency of climate change has increased scrutiny of companies’ ESG (Environmental, Social, and Governance) practices. Investors are now more inclined to support firms that demonstrate strong ESG commitments, often willing to pay a green premium for sustainable investments. However, is the spread in performance between the ‘Sin’ and ‘Saint’ stocks driven by the ESG factor or some other omitted variable? The recent study by Zhan Shi and Shaojun Zhang suggests that the hidden force that may be in play is the price of the oil.

Can we simplify the complexities of the stock market and distill them into a simple set of quantifiable metrics? A lot of academic papers suggest this, and they offer formulas that should make the life of a stock picker easier. Some of the most compelling methodologies within this realm are the F-Score, Magic Formula, Acquirer’s Multiple, and the Conservative Formula. These quantitative strategies are designed to identify undervalued stocks with robust fundamentals and potential for high returns. But do they really work out-of-sample? A new paper by Marcel Schwartz and Matthias X. Hanauer tries to answer this interesting question…