Perbandingan Kinerja Model ARIMA dan Jaringan Saraf Tiruan (ANN) dalam Memprediksi Jumlah Mahasiswa Baru
DOI:
https://doi.org/10.30812/corisindo.v1.5450Keywords:
ARIMA, Artificial Neural Network, Prediksi Mahasiswa, Time Series, Perencanaan Perguruan TinggiAbstract
Prediksi jumlah mahasiswa baru merupakan aspek krusial dalam perencanaan strategis perguruan tinggi, yang mempengaruhi alokasi sumber daya, perencanaan infrastruktur, dan pengembangan program akademik. Penelitian ini mengkaji penerapan dua metode prediksi time series yang berbeda: AutoRegressive Integrated Moving Average (ARIMA) dan Artificial Neural Network (ANN) untuk memprediksi jumlah mahasiswa baru. Menggunakan data historis penerimaan mahasiswa selama 6 tahun (2019-2024), penelitian ini membandingkan akurasi prediksi kedua metode dalam konteks perencanaan perguruan tinggi. Hasil penelitian menunjukkan bahwa metode ANN memberikan akurasi prediksi yang lebih tinggi dengan nilai MAPE 11.65% dibandingkan ARIMA dengan MAPE 17.9%. Evaluasi performa model dilakukan menggunakan metrik evaluasi MSE (Mean Absolute Error), RMSE (Root Mean Square Error), dan MAE (Mean Absolute Error). Model Artificial Neural Network menunjukkan performa yang lebih baik dalam memprediksi jumlah mahasiswa baru dengan tingkat akurasi yang dapat diterima untuk keperluan perencanaan institusi. Namun, ARIMA memberikan interpretabilitas yang lebih baik dalam memahami pola seasonality dan trend jangka panjang.
References
[1] S. Maslamah, A. Nur Handayani, and G.-J. Horng, “Forecasting University Admissions through Student Achievement using Arima Method,” J. Educ. Technol., vol. 9, no. 1, pp. 10–20, 2025, [Online]. Available: https://doi.org/10.23887/jet.v9i1.860
[2] F. A. Fitrony, L. D. Supraba, T. Rantung, I. M. A. Agastya, and K. Kusrini, “Analysis to Predict the Number of New Students At UNU Pasuruan using Arima Method,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 14, no. 1, pp. 123–128, 2025, doi: 10.32736/sisfokom.v14i1.2251.
[3] T. Fang-Mei, Y. Hsiao-Cheng, and T. Gwo-Hsiung, “Combining Neural Network Model with Seasonal Time Series ARIMA model,” Technol. Forecast. Soc. Change, vol. 69, no. 2002, pp. 71–87, 2002.
[4] “No Title,” no. May, 2023.
[5] F. E. James and J. L. Weese, “Neural Network-Based Forecasting of Student Enrollment With Exponential Smoothing Baseline and Performance Analysis,” ASEE Annu. Conf. Expo. Conf. Proc., 2022, doi: 10.18260/1-2--41751.
[6] L. Wang, H. Zou, J. Su, L. Li, and S. Chaudhry, “An ARIMA-ANN Hybrid Model for Time Series Forecasting,” Syst. Res. Behav. Sci., vol. 30, no. 3, pp. 244–259, 2013, doi: 10.1002/sres.2179.
[7] A. Aslanargun, M. Mammadov, B. Yazici, and S. Yolacan, “Comparison of ARIMA, neural networks and hybrid models in time series: Tourist arrival forecasting,” J. Stat. Comput. Simul., vol. 77, no. 1, pp. 29–53, 2007, doi: 10.1080/10629360600564874.
[8] T. W. Mapuwei, J. Ndava, M. Kachaka, and B. Kusotera, “An Application of Time Series ARIMA Forecasting Model for Predicting Tobacco Production in Zimbabwe,” Am. J. Model. Optim., vol. 9, no. 1, pp. 15–22, 2022, doi: 10.12691/ajmo-9-1-3.
[9] M. Valipour, M. E. Banihabib, and S. M. R. Behbahani, “Monthly inflow forecasting using autoregressive artificial neural network,” J. Appl. Sci., vol. 12, no. 20, pp. 2139–2147, 2012, doi: 10.3923/jas.2012.2139.2147.
[10] N. Marisetty, “Forecasting of Selected International Stock Indices Returns By Using Arima Model,” vol. 14, pp. 66083–66091, 2024, [Online]. Available: https://doi.org/10.37118/ijdr.28098.07.2024
[11] A. A. Adebiyi, A. O. Adewumi, and C. K. Ayo, “Comparison of ARIMA and artificial neural networks models for stock price prediction,” J. Appl. Math., vol. 2014, pp. 9–11, 2014, doi: 10.1155/2014/614342.
[12] H. Bousnguar, L. Najdi, and A. Battou, “Forecasting approaches in a higher education setting,” Educ. Inf. Technol., vol. 27, no. 2, pp. 1993–2011, 2022, doi: 10.1007/s10639-021-10684-z.
[13] J. S. Armstrong and F. Collopy, “Error measures for generalizing about forecasting methods: Empirical comparisons,” Int. J. Forecast., vol. 8, no. 1, pp. 69–80, 1992, doi: 10.1016/0169-2070(92)90008-W.
[14] “1994. Time Series Analysis-Forecasting and Control.pdf.”
[15] E. Okewu, P. Adewole, S. Misra, and R. Maskeliunas, “Artificial Neural Networks for Educational Data Mining in Higher Education : A Systematic Literature Review Artificial Neural Networks for Educational Data Mining in Higher Education : A Systematic Literature Review,” Appl. Artif. Intell., vol. 35, no. 13, pp. 983–1021, 2021, doi: 10.1080/08839514.2021.1922847.
