On the Nonlinear Predictability of Stock Returns Using Financial and Economic Variables

Replicated results indicate that, in fact, the switching portfolio based on the recursive neural-network forecasts generates lower accumulated wealth with higher risks than that based on linear regression.

Abstract

In a recent article by Qi, neural networks trained by Bayesian regularization were used to predict excess returns on the S&P 500. The article concluded that the switching portfolio based on the recursive neural-network forecasts generates higher accumulated wealth with lower risks than that based on linear regression. Unfortunately, attempts to replicate the results were unsuccessful. Replicated results using the same software, approach and data detailed by Qi indicate that, in fact, the switching portfolio based on the recursive neural-network forecasts generates lower accumulated wealth with higher risks than that based on linear regression.