Machine Learning in Finance: A Topic Modeling Approach

Abstract

We provide a first comprehensive structuring of the literature applying machine learning to finance. We use a probabilistic topic modeling approach to make sense of this diverse body of research spanning across the disciplines of finance, economics, computer sciences, and decision sciences. Through the topic modelling approach, a Latent Dirichlet Allocation technique, we are able to extract the 14 coherent research topics that are the focus of the 5,204 academic articles we analyze from the years 1990 to 2018. We first describe and structure these topics, and then further show how the topic focus has evolved over the last two decades. Our study thus provides a structured topography for finance researchers seeking to integrate machine learning research approaches in their exploration of finance phenomena. We also showcase the benefits to finance researchers of the method of probabilistic modeling of topics for deep comprehension of a body of literature, especially when that literature has diverse multi-disciplinary actors.

Keywords: topic modeling, machine learning, structuring finance research, textual analysis, Latent Dirichlet Allocation, multi-disciplinary

JEL Classification: G00, G10, C45