Short-term reversal strategies in U.S. large-cap equity indexes, such as the S&P 500, are well-documented and widely followed. These reversals often occur in response to brief periods of market stress, where sharp declines are followed by quick recoveries (as we have experienced in the last few weeks). Traditional approaches typically identify such stress periods using only the price action of the equity index itself. In this research, however, we explore a broader perspective—one that leverages the behavior of other asset classes, including gold, oil, and intermediate-term U.S. Treasuries. We demonstrate that using signals from these correlated assets to detect stress events can enhance the timing and robustness of reversal trades in equities. Furthermore, we show that combining signals across multiple markets leads to a more effective and diversified reversal strategy.

In this study, we explore the application of simple spread trading strategies using Bitcoin ETFs and cryptocurrency infrastructure ETFs—two highly correlated asset classes due to the broader influence of cryptocurrency market movements. Given their strong relationship, this setup provides a compelling case for implementing pair trading strategies based on mean reversion principles. Building on our previous work, How to Build Mean Reversion Strategies in Currencies, we adapt and extend these models to the cryptocurrency ETF space, demonstrating their broader applicability beyond traditional currency markets. Specifically, we test two sub-methods of mean reversion: linear and exponential. Our goal is to offer a clear and practical example of how traders can leverage these techniques across different asset classes.

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.

The year 2024 is nearly behind us, so it’s an excellent time for a short recapitulation. In the previous 12 months, we have been busy again (as usual) and have published over 70 short analyses of academic papers and our own research articles. The end of the year is a good opportunity to summarize 10 of them, which were the most popular (based on the Google Analytics ranking). The top 10 is diverse, as usual; once again, we hope that you may find something you have not read yet …

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.

Over the past few years, significant shifts in the financial landscape have reshaped the dynamics of global markets, including the cryptocurrency sector. Events such as the ongoing war in Ukraine, rising inflation rates, the soft landing scenario in the US economy, and the recent Bitcoin halving have all profoundly impacted market sentiment and price movements. Given these developments, we decided to revisit and reassess trading strategies, specifically Trend-following and Mean-reversion in Bitcoin published in 2022, which utilized data from November 2015 to February 2022. This new study explores how these strategies would have performed from November 2015 to August 2024, taking recent changes into account. The study also examines market changes between February 2022 and August 2024, highlighting developments since previous research. Additionally, it evaluates the influence of seasonality on Bitcoin’s price action, similar to our previous article – The Seasonality of Bitcoin. By analyzing these factors, we aim to provide deeper insights into the evolving behavior of the world’s leading cryptocurrency and guide investors through the complexities of today’s market environment.