Cryptocurrencies are attracting much attention, even becoming a priority for many high-net-worth investors. The introduction of the new spot Bitcoin ETFs simplifies access to this asset class, and as cryptos are included in more and more portfolios, industry practitioners look for models that can help assess how big a portion of clients’ portfolios allocate to this new asset class. Factor risk models are an industry standard for understanding other main asset classes, and authors of today’s presented research (Akbari, Ekponon, and Guo, revised 2024) provide useful insights into which factor risks can explain the variation in cryptos returns.

The main take-away? We can definitely shred the idea that crypto stands on its own, acting independently and in isolation from other financial world vehicles. Overall, these findings provide the evidence that well-known factor risks can explain crypto market returns and that a strong link exists between the crypto market and traditional asset classes.

Commodity Trading Advisor (CTA) funds are commonly associated with managed futures investing; however, beyond commodities, they have the flexibility to venture into other assets, including interest rates, currencies, fixed income, and equity indices. Most of the CTA strategies are trend-following, taking long positions in markets experiencing upward trends and short positions in markets undergoing downward trends, with the expectation that these trends will persist. CTA funds demonstrate a negative correlation with traditional assets, especially evident during periods of pronounced downturns in equity markets, and this characteristic positions them as an appealing alternative investment option, serving as a protective measure against extreme events in financial markets. We aim to explore these trend-following strategies by creating a “CTA proxy” using ETFs across all asset classes. Using ETFs allows for maintaining the diversification of CTA funds and represents an alternative with easier data availability compared to futures contracts. Additionally, we are very interested in seeing the contribution of the short leg of CTA sub-strategies to performance, as we have a hypothesis that we can significantly improve the risk-return profile of the CTA strategies by removing a short leg portion of the strategy from some assets.

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?

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.