Stock Price Forecasting on Telecommunication Sector Companies in Indonesia Stock Exchange Using Machine Learning Algorithms

Abstract

Stock investment is a demand-driven and demanding monetary practice. Hence, the study of stock forecasts or, more precisely, the forecasting of stock prices, plays an essential role in the stock market. Mistakes in forecasting share prices have a significant impact on global finance; thus, they require an effective method of predicting changes in share prices. Machine learning is one of the methods that can be used to predict the stock price. To predict the stock price of five companies in the telecommunications sector, Bakrie Telecom Tbk (BTEL), PT. XL Axiata Tbk (EXCL), PT. Smartfren Telecom Tbk (FREN), PT. Telekomunikasi Indonesia Tbl (TLKM), and PT. Indosat Tbk (ISAT), two algorithms are used to predict the stock prices, which are the Gaussian Process and SMOreg and train dataset from January 1, 2017, to December 31, 2019. The result of this study is SMOreg has the best result than the Gaussian Process with an RMSE value of 0.00005, MAPE 1.88%, and MBE 0.00025.