A Comparative Analysis of Classical and Quantum Computer Trading Algorithms

Abstract

Quantum computing has the potential to revolutionize the field of investing. By using quantum algorithms utilizing mean regression, long short-term memory networks, and neutral tree networks, investors can better understand complex financial markets and make more informed decisions. This research report investigates the potential benefits of quantum computing for portfolio optimization by comparing a classical algorithm that used standard statistical mean regression and a quantum computer algorithm, both analyzing the same dataset of historical stock prices and volatility to create perfectly traded portfolios. The quantum algorithm was able to create a better portfolio than the classical algorithm, even when given the same dataset, with the classical algorithm performing with a Sharpe Ratio of 1.23 for a chosen basket of stocks, and 0.77 for the S&P500 index, and the quantum computing algorithm performing with a Sharpe Ratio above 4, in some cases. This result suggests that when given the same data, quantum computers have better pattern recognition capabilities than classical computers, given their larger computing parameters, and that they have the potential to create better portfolios.