Indonesia Infrastructure and Consumer Stock Portfolio Prediction using Artificial Neural Network Backpropagation S. Prashant Mahasagara 1 , Andry Alamsyah 2 , Brady Rikumahu 3 School of Economics and Business Telkom University, Bandung, Indonesia 1 mahasagara@students.telkomuniversity.ac.id 2 andrya@telkomuniversity.ac.id, 3 bradyrikumahu@telkomuniversity.ac.id 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. Keywords— Stock Portfolio, Artificial Neural Network, Backpropagation I. INTRODUCTION Indonesia has small ratio number of investor comparing to total population [1, 2], the investment has not reached 1 percent of total population. This indicates there are some obstacles to become an investor in Indonesian Stock market. The obstacles can be unstable economic condition, lack of education in investment and inadequate bureaucracy. Investor objective is to get optimize return between risk and return. Uncertain return is risks of an investment. Stock price predicting is needed so investor know possible price in the future, minimize the uncertainty. There are many methods that can be used in predicting the price. Two main methods are the fundamental and technical methods. The fundamental method focuses on the condition of the company and technical method focuses on historical price of a stock without considering the fundamental aspects. As investor, we want to have certain return on our investment. But certainty is hard to predict. Stock historical price as big data has the unique pattern. The exploration of pattern is data analytics objective. Generally, data analytics techniques are description, estimation, association, clustering, classification and prediction [3]. With time-series or historical data we can build a predictive model with data analytics to predict the future condition [4]. Compared with many prediction approach, e.g. Logistic Regression, Vector Autoregressive and Autoregressive Integrated Moving Average, ANN has most accurate prediction results [5, 6, 7]. ANN based computing systems by modeling Biological Neural Systems [8, 9] and possible to study patterns of calculation that generates a prediction of which is desirable due to its ability to process with forward propagation and back propagation. With the advantage capable of processing large amounts of data, ANN Backpropagation generates predictions that have small error rate [10, 11]. The previous research [7, 8, 9, 10, 11] on prediction stock price didn’t continue to the next stage, eventhough the ANN result has high accuracy. In this work, we continue the prediction of stock price to forming portfolio with objective of know performance of portfolio prediction using ANN. II. THEORITICAL BACKGROUND A. Theoretical Framework The idea of this research based on 2 underlying theories, Finance Management, Big Data and Data analytics. It is shown on the Fig. 1., the linkages between both theories is stock price prediction, then the stock price prediction result formed into portfolio of stock investment. B. Investment, Diversification & Portfolio Diversification is the solution to minimize the risk of some investment. The example implementation of diversification is forming portfolio. This help investor for deciding investment on basis fund proportion. 2017 Fifth International Conference on Information and Communication Technology (ICoICT) ISBN: 978-1-5090-4911-0 (c) 2017 IEEE