Cross-sectional trading

This paper investigates whether longer historical training periods improve the out-of-sample performance of a Hidden Markov Model (HMM) used for identifying financial market regimes. Four four-state Gaussian HMMs are compared, differing only in the starting point of their training data (1970, 1980, 1990, and 2000), while being evaluated on the same test period. The model uses five market-based features capturing volatility, drawdowns, credit conditions, and sector rotation to identify latent risk regimes.

The study highlights that validation methodology and evaluation criteria are as important as model design and data length when assessing regime-based investment models.

Currency strategies often appear simple on the surface – go long high-yielding currencies, short low-yielding ones, or take a position on the U.S. dollar. But these trades actually mix two distinct components: a Dollar component, which bets on broad movements of the U.S. dollar against all others, and a Cross-Sectional (CS) component, which exploits relative differences across countries. The question is, which of these components really drives currency risk premia? A new paper by Vahid Rostamkhani tackles this long-standing question by decomposing the predictive power of eleven macroeconomic fundamentals—such as interest rates, inflation, unemployment, and fiscal variables—into these two components across almost a century of data (1926-2023). This approach directly tests whether it is more rewarding to time the dollar itself or to focus on cross-country fundamental spreads.