Indonesia infrastructure and consumer stock portfolio prediction using artificial neural network backpropagation

Abstract

Artificial Neural Network (ANN) method is increasingly popular to build predictive model that generated small error prediction. To have a good model, ANN needs large dataset as an input. ANN backpropagation is a gradient decrease method to minimize the output error squared. Stock price movements are suitable with ANN requirement: it is a large data set because stock price is recorded up to every seconds, usually called high frequency data. The implementation of stock price prediction using ANN approach is quite new. The predictive model help investor in building stock portfolio and their decision making process. Buying some stocks in portfolio decrease diversified risk and increases the chance of higher return. In this paper, we show how to generate prediction model using artificial neural network backpropagation of stock price and forming portfolio with predicted price that bring prediction of the portfolio with the smallest error. The data set we use is historical stock price data from ten different company stocks of infrastructure and consumer sector Indonesia Stock Exchage. The results is for lower risk condition, ANN predictive model gives higher expected return than the return from real condition, while for higher risk, the return from the real condition is higher than the ANN predictive model.