Stock Price Modelling of Ciputra Development Tbk. (CTRA) Using Fourier Series

Ika Purnamasari (Doctoral Study Program MIPA, Faculty of Science and Technology, Airlangga University, Indonesia)
Toha Saifudin (Department of Mathematics, Faculty of Science and Technology, Universitas Airlangga, Indonesia)
Sri Wahyuningsih (Statistics Study Program, Department of Mathematics, Faculty of Mathematics and Natural Sciences, Mulawarman University)
M. Fariz Fadillah Mardianto (Department of Mathematics, Faculty of Science and Technology, Universitas Airlangga, Indonesia)

JOURNAL OF APPLIED INFORMATICS AND COMPUTING
Vol. 10 No. 3 (2026): June 2026

Stock price data generally show fluctuating and dynamic patterns, making the forecasting process challenging in time series analysis. In addition, stock forecasting is also related to economic activity and investment development that support economic growth. This study applies the Fourier series model to predict daily stock prices of Ciputra Development Tbk (CTRA) during January-December 2025 by considering the Fourier parameter (K). The Fourier series estimator consists of two models, namely a model with trend component and a model without trend component. The data were divided into training and testing sets using an 85:15 ratio. Model selection was performed using Generalized Cross validation (GCV), while model performance was evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results show that the Fourier series model with a trend component outperformed the model without trend component. The optimal model was obtained at K=20 with a minimum GCV value of 357.7702. The model produced a training MAPE of 1.2804% and RMSE of 14.9427, while the testing MAPE and RMSE were 5.0640% and 53.6083, respectively, indicating good predictive accuracy and generalization performance.