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.

Active Share is a popular metric used to gauge how actively managed a portfolio is compared to its benchmark, but its predictive power for fund performance is questionable. Our research suggests that high Active Share often reflects exposure to systematic equity factors rather than genuine stock-picking skill. Additionally, inaccuracies in benchmark selection can distort the metric’s insights, making it unreliable as a standalone measure. A more effective approach is to conduct a factor analysis of alpha to better understand a manager’s performance and true sources of over/underperformance.

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.

Short sellers often have a bad reputation, seen as market disruptors who profit from declining prices. Yet, they play a crucial role in making markets more efficient by identifying overvalued assets and correcting mispricings. A recent study uncovers another surprising aspect of their behavior: rather than just demanding liquidity, the most informed short sellers actually provide it. Using transaction-level data, the research shows that these traders supply liquidity, especially on news days and when trading on known anomalies, challenging the conventional view of short sellers as merely aggressive market participants.

Today, we will venture a little into the fundamental analysis corner, and we will give you a glimpse of an intriguing paper (Hillenbrand and McCarthy, 2024) that discusses the advantages of using ‘Street’ earnings over traditional GAAP earnings. The paper suggests that ‘Street’ earnings provide better valuation estimates and improved financial analysis. Is this a way how to improve the performance of the struggling equity value factor?

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.