Application of Machine Learning in Behavioral Finance: An Overview

ABSTRACT

Machine learning (ML) is currently underutilized in behavioral economics due to a lack of expertise with the approach. The next generation of scientists, on the other hand, who have grown up with machine learning, will eventually enter it. Machine learning and behavioral economics interactions have the potential to be mutually beneficial. On the one hand, machine learning may be used to sift through massive amounts of data in search of behavioral-type traits that lead to the production of a variety of behaviors. Behavioral economics is a discipline of economics that looks at how psychological, cognitive, emotional, cultural, and social aspects impact human decisions and how they deviate from what rational reasoning predicts. In other words, humans will be viewed as insufficiently rational agents, with psychological factors, as well as environmental factors, emphasized as major determinants of human actions. This method improves human behavior prediction and allows for the creation of nudge policies to improve people decisions in instances where directed deviations from logical thinking occur. ML algorithms that are incorporated to detect biases and false assumptions, on the other hand, would perform better. This research aims to give knowledge of the first-mentioned application of ML in behavioral finance, which is identifying characteristics that are significant for people behavior and sentiment, which are reflected during decision making. This article, in particular, provides a fundamental overview of how ML techniques like as Random Forest, Gradient Boosting, and k-Nearest Neighbors Machine learning approaches can help with research in the field of behavioral finance.

FULL TEXT