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.

Seasonality plays a significant role in financial markets and has become an essential concept for both practitioners and researchers. This phenomenon is particularly prominent in commodities, where natural cycles like weather or harvest periods directly affect supply and demand, leading to predictable price movements. However, seasonality also plays a role in equity markets, influencing stock prices based on recurring calendar patterns, such as month-end effects or holiday periods. Recognizing these patterns can provide investors with an edge by identifying windows of opportunity or risk in their investment strategies.

In this article, we explore the historical performance of sector momentum strategies and examine how their alpha has diminished over time. By analyzing the underlying causes behind this decline, we identify key factors contributing to the underperformance. Most importantly, we introduce an enhanced approach to sector momentum, demonstrating how this solution significantly improves the performance of an ETF sector momentum strategy, making it once again an effective tool for systematic investors.

Sector/industry picking or country picking can be a profitable trading style but is usually much more challenging than it seems at first sight. Building a good trading model requires a lot of research and dedication. Unfortunately, due to the limited numbers of industries and countries, sorting them on aggregate characteristics can wash out important cross-sectional variations in the characteristics and lead to concentrated portfolios prone to noisier realized returns.

In their fresh Dimensional Fund Advisors research piece, Dong, Huang, and Medhat (2023) touch on the question of whether investors should systematically emphasize certain industries or countries to increase expected returns. Their overhead view provides new insights and sums that investors will likely be better off pursuing premiums in the larger cross-section of individual securities and maintaining broad diversification across the smaller cross-sections of industries and countries.