Portfolio selection using neural networks

TL;DR

This paper introduces a neural network heuristic for portfolio selection that accounts for realistic constraints, demonstrating competitive results compared to existing methods.

Contribution

It presents a novel neural network-based heuristic for the portfolio optimization problem with cardinality and bounding constraints.

Findings

Neural network heuristic effectively traces the efficient frontier.

Results are comparable or superior to previous heuristics.

The method handles realistic investment constraints.

Abstract

In this paper we apply a heuristic method based on artificial neural networks in order to trace out the efficient frontier associated to the portfolio selection problem. We consider a generalization of the standard Markowitz mean-variance model which includes cardinality and bounding constraints. These constraints ensure the investment in a given number of different assets and limit the amount of capital to be invested in each asset. We present some experimental results obtained with the neural network heuristic and we compare them to those obtained with three previous heuristic methods.