A Systematic Literature Review of Classical and Quantum Machine Learning Approaches for Mutual Fund Portfolio Optimization

Quantum Computing is a dynamic field which has evolved since its inception around 3 decades back, to the development of various powerful algorithms including Quantum Approximate Optimization Algorithm (QAOA) and Variational Quantum Eigensolver (VQE) to name a few. Today's quantum computers are not as powerful as the current breed of supercomputers. However, the existing breed of NISQ (Noisy Intermediate Scale Quantum) quantum computers have a significant potential to provide faster solutions to problems in various domains which are not just relevant for the present but also for the future such as Quantum Machine Learning in the Fintech domain. Portfolio Optimization (PO) is one such problem in research and the financial services industry at large. In principle, Quantum Computing, makes it possible to arrive at an optimal portfolio composition for a high return and low risk investment much faster than any existing supercomputer today. This review paper examines literature on classical and quantum machine learning approaches for Mutual Fund PO, analyzing 44 papers from 2003 to 2023. PO being a vast topic, we limit our scope to Mutual Funds and its driver that is the equity markets. We provide an overview to the types of problems, preferred approaches, their benchmarks, deduced conclusions, and research gaps as a comprehensive survey for diverse readers.