COMPARISON OF ACCURACY BETWEEN NEURAL NETWORK AND REGRESSION MODELS IN FORECASTING

Hermansah Hermansah, Muhammad Muhajir

Abstract


This research discusses the forecasting of the median value of owner occupied homes (MEDV) using all the other continuous variables available in the Boston dataset. The Boston dataset is a collection of data about housing values in the suburbs of Boston. The used method is Feed Forward Neural Network (FFNN) and the multiple linear regression method as a comparison. The result of the research indicates that the FFNN method is better than multiple linear regression in forecasting the median value of owner occupied homes (MEDV) using all the other continuous variables available in the Boston dataset. It is proven that the MSE and MAPE value of using the FFNN method is 15.7518 and 0.14563, whereas the value of multiple linear regression is 31.2630 and 0.21040. Based on this result, the research can be concluded that the FFNN method has the smaller MSE value, the result of the forecasting is more accurate.

Full Text:

PDF


DOI: https://doi.org/10.15548/map.v5i1.5949
Abstract views : 109 times
PDF : 61 times

References


Sari, R., Gunawan. 2015. Arsitektur Jaringan Saraf Tiruan Untuk Pemodelan Proses Ekstraksi Aturan dengan Search Tree. Seminar Nasional Inovasi Desain dan Teknologi, 306-313.

Setiawan, W. 2008. Prediksi harga saham menggunakan jaringan syaraf tiruan multilayer feedforward network dengan algoritma backpropagation. Konferensi Nasional Sistem dan Informatika, 108-113.

Haykin, S. 2004. Neural networks: a comprehensive foundation. Prentice Hall PTR, 2nd Edition.

Sari, I. P., Wuryandari, T., Yasin, H. 2014. Prediksi Data Harga Saham Harian Menggunakan Feed Forward Neural Networks (FFNN) dengan Pelatihan Algoritma Genetika (Studi Kasus pada Harga Saham Harian PT. XL Axiata Tbk). Jurnal Gaussian, 3(3), 441-450.

Faraway, J., Chatfield, C. 1998. Time series forecasting with neural networks: a comparative study using the air line data. Journal of the Royal Statistical Society Series C: Applied Statistics, 47(2), 231-250.

Kao, J. J., Huang, S. S. 2000. Forecasts using neural network versus Box-Jenkins methodology for ambient air quality monitoring data. Journal of the Air & Waste Management Association, 50(2), 219-226.

Kusumadewi, F. 2014. Peramalan Harga Emas menggunakan Feedforward Neural Network dengan Algoritma Backpropagation. Yogyakarta: Universitas Negeri Yogyakarta.

Suhartono, S. 2005. Neural Networks, ARIMA and ARIMAX Models for Forecasting Indonesian Inflation. Widya Journal of Management and Accounting, 5(3), 219732.

Siang, J. J. 2005. Jaringan syaraf tiruan dan pemrogramannya menggunakan Matlab. Penerbit Andi, Yogyakarta.

Warsito, B. 2006. Perbandingan Model Feed Forward Neural Network dan Generalized Regression Neural Network pada Data Nilai Tukar Yen terhadap Dolar AS. Prosiding SEMINAR NASIONAL SPMIPA, 1(1), 127-131.

Meinanda, M. H., Annisa, M., Muhandri, N., Suryadi, K. 2009. Prediksi masa studi sarjana dengan artificial neural network. Internetworking Indonesia Journal, 1(2), 31-35.

Suhartono, S. 2007. Feedforward Neural Networks untuk Pemodelan Runtun Waktu. Yogyakarta: Universitas Gadjah Mada.

Fajar, M., Jatmiko, W. 2011. Implementasi Feedforward Neural Network pada Field Programmable Gate Array untuk Mendeteksi Sleep Apnea menggunakan Data Ekstraksi ECG. Konferensi Nasional Sistem dan Informatika, 290-296.

Farber, R., Lapedes, A. 2008. How Neural Nets Works. Evolution, Learning, and Cognition, 331-345.

Bambang, B., Widodo, R. J., Sutalaksana, I. Z., Singgih, M. L. 2004. Teknik Jaringan Syaraf Tiruan Feedforward Untuk Prediksi Harga Saham Pada Pasar Modal Indonesia. Jurnal Informatika, 1(1), 33-37.

Handaga, B., Asy’ari, H. 2012. Kombinasi Algoritma Cuckoo-Search Dan Levenberg-Marquadt (CS-LM) pada Proses Pelatihan Artificial Neural Network (ANN). Simposium Nasional RAPI XI FT UMS.

Fausett, L. V. 2006. Fundamentals of neural networks: architectures, algorithms and applications. Pearson Education India.

Hermansah, Rosadi, D., Abdurakhman, Utami, H. 2020. Selection of input variables of nonlinear autoregressive neural network model for time series data forecasting. Media Statistika, 13(2), 116-124.

Hermansah, Rosadi, D., Abdurakhman, dan Utami, H. 2021. Automatic time series forecasting using nonlinear autoregressive neural network model with exogenous input. Bulletin of Electrical Engineering and Informatics, 10(5), 2836-2844.

Hermansah, Rosadi, D., Abdurakhman, dan Utami, H. 2021. A comparison of learning algorithms for seasonal time series forecasting using NARX model. Journal of Mathematical and Computational Science, 11(6), 6638-6656.

Hermansah, Rosadi, D., Abdurakhman, dan Utami, H. 2021. Time series forecasting with trend and seasonal patterns using NARX network ensembles. Mathematics and Statistics, 9(4), 511-520.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

 

Lisensi Creative Commonsis licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.