Clustering-Based Cross-Sectional Regime Identification for Financial Market Forecasting

Regime switching analysis is extensively advocated in many fields to capture complex behaviors underlying an ecosystem, such as the economic or financial system. A regime can be defined as a specific group of complex patterns that share common characteristics in a specific time interval. Regime switch, caused by external and/or internal drivers, refers to the changing behaviors exhibited by a system at a specific time point. The existing regime detection methods suffer from two drawbacks: they lack the capability to identify new regimes dynamically or they ignore the cross-sectional dependencies exhibited by time series data for the forecasting. This promoted us to devise a cluster-based regime identification model that can identify cross-sectional regimes dynamically with a time-varying transition probability, and capture cross-sectional dependencies underlying financial time series for market forecasting. Our approach makes use of a nonlinear model to account for the cross-sectional regime dependencies, neglected by most existing studies, that can improve the performance of a forecasting model significantly. Experimental results on both synthetic and real-world dataset demonstrate that our model outperforms state-of-the-art forecasting models.