Using Textual Analysis to Diversify Portfolios

Abstract

Semantic fingerprinting is a leading AI solution that combines recent developments from cognitive neuroscience and psycholinguistics to analyze text with human-level accuracy. As an efficient method of quantifying text, it has already found its application in finance where the semantic fingerprints of company descriptions have been shown to successfully predict stock return correlations of Dow Jones Industrial Average (DJIA) constituents. By extension, it has been suggested that diversified portfolios could be constructed to exploit the fundamental (dis)similarity between companies’ core activities (measured by the semantic overlap of company descriptions). This paper follows the performance of two portfolios made of the same DJIA constituent companies: the “minimum semantic concentration” portfolio (constructed with text-based portfolio weights) and the traditional “minimum variance” portfolio, over a time span of 16 years including two high volatility events: the 2007 − 2009 financial crisis and the COVID pandemic. The results confirm that textual analysis using semantic fingerprinting is consistently successful in predicting stock return correlations and is valuable as a portfolio selection criterion. However, in times of high market volatility the fundamental information given by the companies’ core activities, while still relevant, might carry less weight.