Weighted Moving Average Passive Aggressive Algorithm for Online Portfolio Selection

Passive aggressive algorithms for online portfolio selection, such as PAMR, were recently shown empirically to achieve state-of-the-art performance in various stock markets. Inspired by the multi-period mean reversion principle in Antic or Algorithm, we present a passive aggressive algorithm by introducing a moving averaged loss function and achieve a novel online portfolio selection strategy named "Weighted Moving Average Mean Reversion" (WMAMR). The strategy is able to effectively exploit the power of mean reversion for online portfolio selection. Extensive experiments on various real markets demonstrate the effectiveness of our strategy in comparison with PAMR, especially with transaction cost.