Investment Strategy via Lead Lag Effect using Economic Causal Chain and SSESTM Model

Kei Nakagawa, Shingo Sashida, Hiroki Sakaji

Abstract: In the fields of academic and practical finance, many text mining approaches have been used. The economic causal chain is one example and refers to a cause-and-effect network structure among companies. It is constructed by extracting texts indicating causal relationships from the texts of financial statement summaries. A previous study showed there is a lead-lag effect that spreads to the ’effect’ stock group when a large stock price fluctuation in the ’cause’ stock group in the causal chain occurs. However, there is room for extracting a more robust lead-lag relationship by giving sentiment to the economic causal chain. The SSESTM (Supervised Sentiment Extraction via Screening and Topic Modeling) model has been proposed as a sentiment analysis specialized for stock return forecasting, and it produced a substantial profit in the U.S. and Japanese stock markets. In this study, we propose an investment strategy that exploits the lead-lag effect in the causal chain relationship considering the sentiments with the SSESTM model. We confirm the profitability of our proposed strategy and there is evidence of stock return predictability across causally linked companies considering sentiment.