SSAAM: Sentiment Signal-based Asset Allocation Method with Causality Information

TL;DR

The paper tackles whether financial news can improve tactical equity allocation by constructing a polarity index from MLM-based sentiment scores and linking it to regime changes. It introduces a four-step SSAAM framework: polarity-index creation, demonstration of leading effects via VAR-LiNGAM, change-point detection with Binary Segmentation, and regime-dependent EVaR optimization for portfolio rebalancing. Empirical results on NYSE FANG+ stock data and financial news show that the polarity index leads the portfolio and that CPD-EVaR++ outperforms competitors, particularly under regime-5 settings with irregular rebalances. The work highlights the practical value of financial text as an active-management signal and points to extensions into multi-asset and macro-policy contexts.

Abstract

This study demonstrates whether financial text is useful for tactical asset allocation using stocks by using natural language processing to create polarity indexes in financial news. In this study, we performed clustering of the created polarity indexes using the change-point detection algorithm. In addition, we constructed a stock portfolio and rebalanced it at each change point utilizing an optimization algorithm. Consequently, the asset allocation method proposed in this study outperforms the comparative approach. This result suggests that the polarity index helps construct the equity asset allocation method.