Machine Learning will quite certainly continue to be a hot topic in 2024, and we are committed to bringing you new developments and keeping you in the loop. Today, we will review original research from Demirbaga and Xu (2023) that highlights the critical role of machine learning model execution time (combination of time for ML training and prediction) in empirical asset pricing. The temporal efficiency of machine learning algorithms becomes more pivotal, given the necessity for swift investment decision-making based on the predictions generated from a lot of real-time data. Their study comprehensively evaluates execution time across various models and introduces two time-saving strategies: feature reduction and a reduction in time observations. Notably, XGBoost emerges as a top-performing model, combining high accuracy with relatively low execution time compared to other nonlinear models.

The primary motivation behind our study stems from an observation of the Global Tactical Asset Allocation (GTAA) strategies throughout the existing papers – the majority of them require relatively frequent rebalancing from the point of view of the ordinary investor. Portfolio rebalancing is usually done on a weekly or monthly basis, and while this period may seem overly boring and slow for the majority of traders (who like to trade on intraday or daily basis), fans of GTAA strategies are not traders; they are investors. Of course, some like to follow the ebbs and flows of the market. But a lot of investors just want to have a life. The financial market is not their hobby. However, on the other hand, they also do not want to hold just the passive buy & hold portfolio. Recognizing the demand for the semi-active strategy, we introduce our novel Pragmatic Asset Allocation.

Dear readers & clients,

So, what are the main highlights?

Six new strategies have been added. Seven new related research papers have been included into existing strategy reviews and two short free Quantpedia blog has been published during last few weeks. Plus, four trading strategies have been backtested in QuantConnect in the previous two weeks.

Investing in emerging markets (EM) or developed markets (DM) outside of the United States tends to follow cyclical trends. At times, it becomes popular and crowded to focus solely on U.S. stocks, while in other periods, the trend shifts to favor everything except U.S. equities. This inclination often relies on historical and past performance data, although it doesn’t guarantee identical outcomes in the future. But what drives these periods of popularity? When do U.S. markets outperform Emerging Markets or other Developed Markets? When do large-cap stocks outperform small-cap stocks, and when do growth stocks outperform value stocks? Are those ebbs and flows in the performance of major thematic investments somehow interlinked, and can we uncover some insights into why this occurs? Those are the questions we will try to answer in the following analysis.

As usual, at this time of the year, let us do a short recapitulation of posts on our blog in the previous 12 months. We have published over 75 short analyses of academic papers and our own research articles on this blog in 2023. We want to use this opportunity to summarize 10 of them, which were the most popular (based on the Google Analytics tool). The top 10 is really diverse; maybe you will be able to find something you have not read yet …