Neural network forecasts of Canadian stock returns using accounting ratios

This study compares neural network forecasts of one-year-ahead Canadian stock returns with the forecasts obtained using ordinary least squares (OLS) and logistic regression (logit) techniques. The input data are 61 accounting ratios for 2352 Canadian companies over the period 1976–1993. The most recent 6 years of data are rolled forward each year to forecast annual returns for 1983–1993. Our results indicate that back propagation neural networks, which consider non-linear relationships between input and output variables, outperform the best regression alternatives for both point estimation and in classifying firms expected to have either high or low returns. The superiority the neural network models translates into greater profitability using various trading rules. Classification models outperform point estimation models, but four to eight output categories appear to give better results for both logit and neural network models than either binary classification models or models with 16 classification categories.