Optimizing Linear Models With Deep Neural Networks: A Case Study on Gambling Data Across Indonesian Provinces

Astri Ayu Nastiti; Abdurakhman Abdurakhman

doi:10.22146/jmt.108379

Optimizing Linear Models With Deep Neural Networks: A Case Study on Gambling Data Across Indonesian Provinces

https://doi.org/10.22146/jmt.108379

Astri Ayu Nastiti^(1*), Abdurakhman Abdurakhman⁽²⁾

(1) Universitas Gadjah Mada
(2) Universitas Gadjah Mada
(*) Corresponding Author

Abstract

Linear regression analysis is a common method that are free to vary and are subject to error. In this study we used hybrid of linear regression and its family to Deep Neural Network (DNN) to fill these gaps. In this paper analyze the phenomenon of gambling in Indonesia in 2018. Results show that the hybrid model is significantly superior to the single model, with the hybrid linear model reducing RMSE by 15.9% and MAPE by 16.2% compared to the single linear model. The hybrid ridge model showed small but consistent improvements in RMSE and MAPE. The most notable improvement was seen in the hybrid lasso model which reduced RMSE by 34.1% and MAPE by 47.1% over the single lasso model. The hybrid elastic net model also showed improved performance with a decrease in RMSE by 16.9% and MAPE by 18.3%. In conclusion, the integration of traditional regression methods with DNN in this hybrid model offers a significant improvement in prediction accuracy, making it a more effective and efficient tool in the analysis of gambling phenomena.

Keywords

Linear regression, ridge regression, LASSO regression, elastic net regression, Deep Neural Network, Hybrid Model

Full Text:

PDF

References

Chan, J. Y. L., Leow, S. M. H., Bea, K. T., Cheng, W. K., Phoong, S. W., Hong, Z. W., & Chen, Y. L. (2022). Mitigating the multicollinearity problem and its machine learning approach: a review. Mathematics, 10(8), 1283.

Khoerunisa, D., Nurahmadi, I., Sari, J. A., Wianti, S., & Siregar, Y. E. Y. (2024). JUDI ONLINE SEBAGAI FAKTOR PENYEBAB PERMASALAHAN PERCERAIAN DI KABUPATEN BEKASI:(Studi Kasus Pada Kecamatan Cikarang Utara Kabupaten Bekasi). Kultura: Jurnal Ilmu Hukum, Sosial, dan Humaniora, 2(2), 63-70.

Jadidah, I. T., Lestari, U. M., Fatiha, K. A. S., Riyani, R., & Wulandari, C. A. (2023). Analisis maraknya judi online di Masyarakat. Jurnal Ilmu Sosial Dan Budaya Indonesia, 1(1), 20-27.

Ludbrook, J. (2010). Linear regression analysis for comparing two measurers or methods of measurement: but which regression?. Clinical and Experimental Pharmacology and Physiology, 37(7), 692-699.

McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5, 115-133.

Vidaurre, D., Bielza, C., & Larranaga, P. (2013). A survey of L1 regression. International Statistical Review, 81(3), 361-387.

Wahkidi, L., Puspitasari, E., & Tamrin, T. (2022). HUBUNGAN TINGKAT KECANDUAN DENGAN TINGKAT KECEMASAN PELAKU JUDI ONLINE DI WILAYAH KECAMATAN TOROH. Jurnal Ilmu Keperawatan Komunitas, 5(2), 68-76.

Tibshirani, R. (1996). Regression Shrinkage and Selection via the Lasso. Journal of The Royal Statistical Society, Vol. 58, No.1, Hal. 267-288. Weisstein, Eric W. "Vector Norm". mathworld.wolfram.com. Retrieved 2020-08-24.

Zhang, Z., Lai, Z., Xu, Y., Shao, L., Wu, J., & Xie, G. S. (2017). Discriminative elastic-net regularized linear regression. IEEE Transactions on Image Processing, 26(3), 1466-1481.

Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society Series B: Statistical Methodology, 67(2), 301-320.

DOI: https://doi.org/10.22146/jmt.108379