Modern Machine Learning Solutions for Portfolio Selection

Abstract

The primary goal of any financial investor is to maximize returns and minimize risks. The selection of the right assets and appropriate allocation of principal wealth is highly essential for the same. Investment specialists and portfolio managers have to manually analyze assets, determine potential returns and risks, and adhere to client preferences to create optimal portfolios. It is a complex and grueling process and demands significant skill and relevant experience for success. Like all other sectors in finance, machine learning models have seen tremendous success in the portfolio selection problem as well. In this article, a thorough review of several machine learning portfolio optimization techniques such as clustering based, Support Vector Machines based, genetic algorithm based, and more has been presented. This article, in its entirety, condenses and interprets the numerous approaches and the merits and limitations corresponding to their implementation. The conclusions presented by this review can be utilized to identify the advantages of these papers. This will help future researchers in their study of the domain and ensure the availability of essential data for further analysis in a systematic and comprehensive manner. With the help of this article, researchers will be well placed to identify areas that present scope for improvement and come up with novel or possibly hybrid techniques to achieve near perfection in portfolio selection.