Selective presentation learning for neural network forecasting of stock markets

This paper proposes a selective presentation learning technique for improving the learnability and predictability of large changes by back-propagation neural networks. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events into account. Training data corresponding to large changes of prediction-target time series are presented more often, and network learning is stopped at the point that has the maximal profit. When this technique is applied to daily stock-price prediction, the prediction error on large-change data was reduced by 11%, and the network's ability to make profits through experimental stock-trading was improved by 67% to 81%, in comparison with results obtained using conventional learning techniques.