Hybrid Autoregressive Integrated Moving Average-Support Vector Regression for Stock Price Forecasting

Abstract

Stock investment provides high-profit opportunities but also has a high risk of loss. Investors use various decision-making methods to minimize this risk, such as stock price forecasting. This research aims to predict daily closing stock prices using a hybrid Autoregressive Integrated Moving Average (ARIMA)-Support Vector Regression (SVR) model and compare it with the single model of ARIMA and SVR, as well as compiling the R-shiny web for the hybrid ARIMA-SVR model which makes it easier for investors to use the model to support investment decision making. The hybrid ARIMA-SVR model is composed of two components: the linear component from the results of stock price forecasting using the Autoregressive Integrated Moving Average (ARIMA) model and the nonlinear components from the residual forecasting results of the ARIMA model using the Support Vector Regression (SVR) model. The data used was closing stock price data from April 1, 2019, to April 1, 2021, from PT Unilever Indonesia Tbk (UNVR.JK), PT Perusahaan Gas Negara Tbk (PGAS.JK), and PT Telekomunikasi Indonesia Tbk (TLKM.JK), from the Yahoo Finance website. The research results conclude that the hybrid ARIMA-SVR model has excellent capabilities in forecasting stock prices with the MAPE values ​​for UNVR, PGAS, and TLKM stocks, respectively of 0.797%, 2.213%, and 0.993%, which are lower than the MAPE values of ARIMA-GARCH and SVR models. The hybrid model can be an alternative model with excellent capabilities in forecasting stock prices.