Google searches for portfolio management: A risk and return analysis

Abstract

Google search data has proven to be useful in portfolio management. The basic idea is that high search volumes are related to bad news and risk increase. This paper shows additional evidence about the use of Google search volumes in risk management, for the Standard & Poor Industrial index components, from 2004 to 2017. To overcome the (time-series and cross-section) limitations Google imposes on the data download, a re-normalization procedure is presented, to obtain a multivariate sample of volumes which preserve their relative magnitude. The results indicate that the volumes' normalization and the starting portfolio are decisive for the portfolio performances. Correctly normalized Google search volumes yield poor results. This may lead to revise the interpretation of the search volume: it can be considered a risk indicator, but when used in a equally risk contribution portfolio, no evidence of the improvement of the risk-return performances is found.