A Hybrid Predictive Prototype for Portfolio Selection using Probability-based Quadratic Programming and Ensemble Artificial Neural Networks

Abstract

Investors are usually limited by cognitive and emotional biases in their investment decision making and thereby end up making poor portfolio investment decisions. Robo-advisors can assist in overcoming these biases. This paper sought to develop a financial robo-advisor prototype based on hybrid programming by use of ensemble artificial neural networks to predict portfolio returns and variances with input nodes of Ornstein–Uhlenbeck process (OU) and geometric brownian motion (GBM) processes’ estimates. The results were subsequently channeled into a probability quadratic optimization algorithm which considers target return probability and value-at-risk constraints as proxies for investor’s risk tolerance so as to provide the optimal portfolio allocation strategy that minimizes portfolio risk given a prescribed investment horizon and target return.  The results showed that the ensemble artificial neural network method implementation predicted correctly the level of 2 of 5 assets and also predicted correctly the trends of the remaining 3 assets. It however yielded low standard deviations and low returns compared to the OU and GBM estimates for short horizons. The quadratic optimization algorithm supported investment in shorter time horizons since portfolio risk was lowest. Diversified allocation was achieved in the shorter time horizons. Longer horizons allocations were biased towards assets with lower standard deviations. Lowest risk portfolio were the ones with a lower certainty probability of target return and vice versa. This paper is a clear demonstration that ensemble methods are accurate in prediction and that a hybrid programming paradigm is an effective approach to leverage on strengths, speed and functionality of different programming languages; an elixir for multifaceted dissociable programming problems.