Combination of Regression and ARIMA Methods ( Reg – ARIMA ) Stock Price Prediction Model

This research is motivated by the limitations of the ARIMA method, which is only suitable for short-term forecasting and specific periods. Therefore, a combination of Regression and ARIMA methods (Reg- ARIMA) is introduced to predict stock prices over a longer period. The purpose of this study is to implement a combination of Regression and ARIMA methods to build a stock price prediction model. The research methodology involves using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) to measure the accuracy of the generated prediction model. The study results indicate significant variations in MAPE and RMSE values among different stocks, reflecting the performance and liquidity of those stock markets. For example, stocks such as ITMG and UNTR show strong performance, while stocks with low closing values may carry higher risks or slower growth. In conclusion, the Reg-ARIMA combination method is effective in extending the range of stock price forecasting, providing a more accurate alternative compared to using only the ARIMA method. This suggests that this hybrid approach can be used to enhance investment decision-making strategies in the stock market.