AMA-K: Aggressive Multi-Temporal Allocation An Algorithm for Aggressive Online Portfolio Selection

Online portfolio selection is an integral component of wealth management. The fundamental undertaking is to maximise returns while minimising risk given investor constraints. We aim to examine and improve modern strategies to generate higher returns in a variety of market conditions. By integrating simple data mining, optimisation techniques and machine learning procedures, we aim to generate aggressive and consistent high yield portfolios. This leads to a new methodology of Pattern-Matching that may yield further advances in dynamic and competitive portfolio construction. The resulting strategies outperform a variety of benchmarks, when compared using Maximum Drawdown, Annualised Percentage Yield and Annualised Sharpe Ratio, that make use of similar approaches. The proposed strategy returns showcase acceptable risk with high reward that performs well in a variety of market conditions. We conclude that our algorithm provides an improvement in searching for optimal portfolios compared to existing methods.