Adaptive moment estimation for universal portfolio selection strategy

Since Cover’s initial work in 1991, Online Portfolio Selection is undoubtedly one of crucial branches of portfolio optimization problem. The increasing development of high-frequency trading and the explosive growth of data volume increasingly require online portfolio strategies to have fast execution speed. However, almost all existing online portfolio strategies cannot satisfy both effective and full utilization of historical data and fast execution speed simultaneously. To this end, this work proposes the Adaptive Moment Estimation (AME) strategy. The proposed strategy makes effective and full utilization of historical data in an incremental way, which not only achieves improved robustness in performance but also keeps linear time complexity. Theoretical and experimental analysis are respectively established to analyze the effectiveness of the proposed AME strategy. For theoretical analysis, AME’s universality is proved, which illustrates that it can theoretically compete with the benchmark Best Constant Rebalanced Portfolio in hindsight. For experimental analysis, AME achieves good performance on different evaluation metrics, and it can sustain reasonable transaction costs. Thus, it is a robust and excellent strategy with promising practical application prospects.