PREDIKSI KINERJA KEUANGAN PT ASTRA INTERNATIONAL TBK DENGAN REGRESI LINIER DAN EXPONENTIAL SMOOTHING

Abstract

The financial performance of a company can be predicted using various methods, one of which is linear regression and exponential smoothing. This study aims to predict the financial performance of PT Astra International Tbk using linear regression and exponential smoothing methods, as well as combining both methods to obtain more accurate predictions. Financial data from PT Astra International Tbk from 2012-2021 was used in this study. The results of the prediction with linear regression show that the current ratio has the lowest MAPE, while exponential smoothing shows that the debt to equity ratio has the lowest MAPE. In the combination of both methods, the lowest MAPE was obtained in predicting total asset turnover. In the discussion, factors that affect the financial performance of PT Astra International Tbk are discussed for each predicted financial ratio. In conclusion, the combination of linear regression and exponential smoothing can improve the accuracy of financial performance predictions, and the results can be used as a reference in investment decision-making.