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.

For decades, investors and analysts have relied on traditional industry classifications like GICS, NAICS, or SIC to group companies into sectors and peer groups. However, these rigid categorizations often fail to capture the evolving nature of businesses, especially in an era of technological convergence and rapid industry shifts. Machine learning (ML) offers a more dynamic and data-driven alternative by analyzing company visuals—such as logos, product images, and branding elements—to identify similarities that go beyond predefined classifications. A recent study applies this approach to construct new industry groupings and tests them in industry momentum and reversal. The results show that ML-generated groups lead to superior performance, once again highlighting the potential of image-based classification in financial analysis.

For those who have not yet had the chance to read it, we recommend the latest empirical study by Minghui Chen, Matthias X. Hanauer, and Tobias Kalsbach, which shows that design choices in machine learning models, such as feature selection and hyperparameter tuning, are crucial to improving portfolio performance. Non-standard errors in machine learning predictions can lead to substantial portfolio return variations, and authors are highlighting the importance of robust model evaluation techniques.

Studies using machine learning techniques for return forecasting have shown considerable promise. However, as in empirical asset pricing, researchers face numerous decisions around sampling methods and model estimation. This raises an important question: how do these methodological choices impact the performance of ML-driven trading strategies? Recent research by Vaibhav, Vedprakash, and Varun demonstrates that even small decisions can significantly affect overall performance. It appears that in machine learning, the old adage also holds true: the devil is in the details.

Does the investment in sophisticated machine learning algorithm research and development pay off? It is an important question, especially in light of the increasing costs related to the R&D of such algorithms and the possibility of decreasing returns for some methods developed in the more distant past. A recent paper by Azevedo, Hoegner, and Velikov (2023) evaluates the expected returns of machine learning-based trading strategies by considering transaction costs, post-publication decay, and the current high liquidity environment. The obstacles are not low, but research suggests that despite high turnover rates, some machine learning strategies continue to yield positive net returns.

As an old investing adage goes, “Everybody’s a genius in a bull market.” It is easy to fall victim to the Dunning-Kruger effect, where attribution bias makes us mistake our luck for abilities. When the business cycles change, there are great problems with precise stock price predictability. And this is not the only problem for humans, who are baffled by many mental heuristics. Machine learning algorithms experience similar problems, too. What is happening, and why is it so? A new paper by Wang, Fu, and Fan gives an explanation and proposes some remedies …