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.

Seasonality is a well-known phenomenon in the commodity markets, with certain sectors exhibiting predictable patterns of performance during specific times of the year. These patterns often attract investors who aim to capitalize on anticipated price movements, creating a self-reinforcing cycle. But what if you could stay one step ahead of the crowd? By front-running these seasonal trends—buying sectors with expected positive performance (or shorting those with negative seasonality) before their favorable months begin—you can potentially gain a significant edge over traditional seasonality-based strategies. In this blog post, we explore how to construct and backtest a systematic strategy using commodity sector ETFs to exploit this seasonal front-running effect.

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.

Our article explores a simple mean reversion trading strategy applied to FX futures, focusing on identifying undervalued and overvalued currencies to generate returns. Using FX futures rather than spot rates allows for the inclusion of interest rate differentials, simplifying the analysis. The strategy employs two position-sizing methods—linear and exponential—both rebalanced monthly based on currency deviations from their mean. While the linear method offers stability, its returns are limited. In contrast, the exponential method, despite higher risk and deeper drawdowns, ultimately delivers stronger growth and better overall performance by leveraging the mean reversion tendencies of FX pairs.

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.