Adaptation of stochasticity into activation function of deep learning for stock price forecasting

Abstract

Stock market is an example of a stochastic environment in the real world. multilayer perceptron (MLP) is often applied to forecast stock price. However, it is widely used to approximate the input-output mapping deterministically. Hence, this study aims to adapt stochasticity into MLP by introducing the Gaussian process into the sigmoid activation function. In addition, the adapted activation function incorporates Roger-Satchell and Yang-Zhang volatity estimators. Besides, the stochastic activation function was considered as a hyperparameter by applying it either only in training time or in both testing and training time. The stochastic multilayer perceptron (S-MLP) is then applied to forecast one day's highest stock price of eight constituents in FTSE Bursa Malaysia KLCI (FBMKLCI). The result shows that the proposed network is inferior in comparison to MLP except for several constituents. In addition, S-MLP with stochastic activation function during both the training and testing time performs better compared to the presence of stochastic activation function in S-MLP during training time only.