An empirical evaluation of machine learning performance in corporate sales growth prediction

Abstract

Corporate performance prediction has attracted considerable research interest in the investment and financial risk management fields. This study comprehensively examines the ability of machine learning algorithms to integrate analysis of sales growth prediction, with specific focus on random forest, weighted random forest, gradient boosting decision tree, and support vector machine, as well as a least-squares probabilistic classifier. We carried out an experimental comparison study over a dataset comprising real corporate data on the effectiveness of these five machine-learning algorithms. The results showed sufficient performance for some machine-learning algorithms.