The Implementation of Holt-Winters Method to Forecast the Loan Interest Rate of Indonesia

Ansari Saleh Ahmar; Abdul Rahman; Mohd. Rizal Mohd. Isa; Rahmat Hidayat

doi:10.35877/454RI.qems2718

Ansari Saleh Ahmar Department of Statistics, Universitas Negeri Makassar, Makassar, 90223, Indonesia (ID)
Abdul Rahman Department of Mathematics, Universitas Negeri Makassar, Makassar, 90223, Indonesia (ID)
Mohd. Rizal Mohd. Isa Department of Computer Science, National Defence University of Malaysia, Kuala Lumpur, 57000, Malaysia (MY)
Rahmat Hidayat Department of Information Technology, Politeknik Negeri Padang, Limau Manis, Padang, 25164, Indonesia (ID)

https://doi.org/10.35877/454RI.qems2718

Keywords: Holt-winters, loan interest rate, forecasting

Viewed = 0 time(s)

Abstract

This study aimed to anticipate the rupiah loan interest rates at commercial banks in Indonesia by employing the Holt-winters method. This study employs data on rupiah loan interest rates from commercial banks in Indonesia. The data comprises a time series element, with monthly intervals spanning from January 2013 to November 2015, which was obtained from the official website of BPS Indonesia. The study demonstrates that the Holt-winters technique yields the most accurate forecasts, as indicated by a Root Mean Square Error (RMSE) of 0.19720630. The parameters alpha, beta, and gamma, set at 0.6, 0.6, and 0.6 respectively, constitute the optimal configuration for this method. These results indicate that the Holt-winters method is an effective tool for capturing seasonality, trends, and patterns in credit interest rate data, making it a reliable choice for future loan interest rate forecasting. The findings of this study are expected to significantly contribute to strategic decision-making in the banking sector, particularly in risk management and loan interest rate strategy determination.

References

Ahmar, A., Boj, E., Safty, M., Alzahrani, S., & El-Khawaga, H. (2022). Suttearima: a novel method for forecasting the infant mortality rate in indonesia. Computers Materials & Continua, 70(3), 6007-6022. https://doi.org/10.32604/cmc.2022.021382
Bayu, G., Putra, I., & Rusjayanthi, N. (2021). A comparison between backpropagation, holt-winter, and polynomial regression methods in forecasting dog bites cases in bali. Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi), 9(3), 251. https://doi.org/10.24843/jim.2021.v09.i03.p06
Bhagat, S. (2023). Precipitation variations in the central vietnam to forecast using holt-winters seasonal additive forecasting method for 1990 to 2019 trend. IOP Conference Series Earth and Environmental Science, 1216(1), 012019. https://doi.org/10.1088/1755-1315/1216/1/012019
Chen, C. (1996). Some statistical properties of the holtwinters seasonal forecasting method. Journal of the Japan Statistical Society, 26(2), 173-187. https://doi.org/10.14490/jjss1995.26.173
Cordeiro, C. and Neves, M. (2012). How bootstrap can help in forecasting time series with more than one seasonal pattern. AIP Conf. Proc. 1479 (1): 1712–1715. https://doi.org/10.1063/1.4756502
Hani'ah, M., Putri, I., & Ririd, A. (2022). Genetic algorithms for holt winter exponential smoothing parameter optimization in indonesian car sales forecasting. Proceedings of the 2022 Annual Technology, Applied Science and Engineering Conference (ATASEC 2022), 159-171. https://doi.org/10.2991/978-94-6463-106-7_15
Lima, S., Gonçalves, A., & Costa, M. (2019). Time series forecasting using holt-winters exponential smoothing: an application to economic data. AIP Conf. Proc., 2186 (1): 090003. https://doi.org/10.1063/1.5137999
Mardiana, S., Saragih, F., & Huseini, M. (2020). Forecasting gasoline demand in indonesia using time series. International Journal of Energy Economics and Policy, 10(6), 132-145. https://doi.org/10.32479/ijeep.9982
Ord, K., Koehler, A., & Snyder, R. (1997). Estimation and prediction for a class of dynamic nonlinear statistical models. Journal of the American Statistical Association, 92(440), 1621. https://doi.org/10.2307/2965433
Ponziani, R. (2021). Foreign tourists arrival forecasting at major airports in indonesia. IJEBD (International Journal of Entrepreneurship and Business Development), 4(5), 662-670. https://doi.org/10.29138/ijebd.v4i5.1507
Ruliana, R., Rais, Z., Marni, M., & Ahmar, A. S. (2024). Implementation of the Support Vector Regression (SVR) Method in Inflation Prediction in Makassar City. ARRUS Journal of Mathematics and Applied Science, 4(1), 28-35. https://doi.org/10.35877/mathscience2608
Sibuea, N., Ramadhan, A., Aulia, R., Khairunnisa, S., Yendra, R., & Adnan, A. (2022). Comparison of linear regression method and holt-winters method in oil and gas export volume forecasting in indonesia. International Journal of Mathematics Trends and Technology, 68(12), 7-12. https://doi.org/10.14445/22315373/ijmtt-v68i12p502
Trull, Ó., García-Díaz, J., & Troncoso, A. (2020). Stability of multiple seasonal holt-winters models applied to hourly electricity demand in spain. Applied Sciences, 10(7), 2630. https://doi.org/10.3390/app10072630
Zhu, X., Song, Z., Sen, G., Tian, M., Zheng, Y., & Zhu, B. (2022). Prediction study of electric energy production in important power production base, china. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-25885-w