Company classification using machine learning

Abstract

The recent advancements in computational power and machine learning algorithms have led to vast improvements in manifold areas of research. Especially in finance, the application of machine learning enables both researchers and practitioners to gain new insights into financial data and well-studied areas such as company classification. In our paper, we demonstrate that unsupervised machine learning algorithms can visualize and classify company data in an economically meaningful and effective way. In particular, we implement the data-driven dimension reduction and visualization tool t-distributed stochastic neighbor embedding (t-SNE) in combination with spectral clustering. The resulting company groups can then be utilized by experts in the field for empirical analysis and optimal decision making. We are the first to demonstrate how this approach can be implemented in manifold areas of finance by developing a general decision engine. With two exemplary out-of-sample studies on portfolio optimization and company valuation with multiples, we show that the application of t-SNE and spectral clustering improves competitive benchmark models.