A Comparative Evaluation of Predominant Deep Learning Quantified Stock Trading Strategies

Quantified Stock Trading refers to the technique of delegating the buying and selling of stock shares to machines running a programmed algorithm. The objective of this study is to, through comparative analysis, find a deep learning powered quantified trading model that can most effectively help an investment portfolio avert continued loss in adverse market climates. This study first reconstructs three deep learning powered trading models and their associated strategies that are representative of distinct approaches to the problem. It then seeks to compare the performance of these strategies from the perspectives of fully informed vs. projection models, returns, risk vs. reward as well as similarity to the benchmark’s return sequence’s patterns through trading simulations ran on three scenarios when the benchmarks are kept at historical low points for extended periods of time. The results show that in extremely adverse market climates, investment portfolios managed by deep learning powered algorithms are able to avert accumulated losses by generating return sequences that shift the constantly negative CSI 300 benchmark return upward. Among the three, the LSTM model’s strategy yields the best performance.