FORECASTING HEALTH INSURANCE PAYER INCOME: A COMPARATIVE ANALYSIS OF DECISION TREE AND SVR ALGORITHMS

Wilsen Grivin Mokodaser; Tonny Irianto Soewignyo; George Morris William Tangka; Fanny Soewignyo

doi:10.34288/jri.v7i3.369

Authors

Wilsen Grivin Mokodaser Universitas Klabat
Tonny Irianto Soewignyo Universitas Klabat
George Morris William Tangka Universitas Klabat
Fanny Soewignyo Universitas Klabat

(*) Corresponding Author

DOI:

https://doi.org/10.34288/jri.v7i3.369

Keywords:

Insurance, Forecasting, Decision Tree, SVR, Predicting

Abstract

An insurance company is a type of non-bank financial institution that protects clients from risks and collects premiums over a certain period, these facts provide an overview of the insurance business and highlight its role in the economy, this study evaluated the performance difference between the Decision Tree Regressor and Support Vector Regression (SVR) in predicting insurance payer income. The Decision Tree model demonstrated strong predictive accuracy, achieving a Mean Absolute Error (MAE) of approximately 57 million and an R-squared (R²) value of 0.896, meaning it could explain around 89.6% of the variance in the data. Additionally, the model maintained high consistency, as evidenced by 5-fold cross-validation scores ranging from 0.908 to 0.967, indicating strong generalization and low risk of overfitting. In contrast, the SVR model significantly underperformed. It recorded a much higher MAE of over 237 million and a large Mean Squared Error (MSE), reflecting substantial deviations from the actual values. Its R² score of -0.299 suggests that SVR performed worse than a naive mean predictor, failing to identify meaningful patterns. This poor performance was consistent across all cross-validation folds, which also produced negative R² scores. The SVR model’s inadequacy is likely due to the large scale of the income data and the lack of proper preprocessing, such as normalization, or parameter tuning. Overall, these findings clearly demonstrate that the Decision Tree Regressor is a more suitable, accurate, and stable model for predicting insurance payer income.

Downloads

Download data is not yet available.

References

Ardi, A. R. S., Batubara, M., & Harahap, M. I. (2022). Pengaruh Pendapatan Premi, Hasil Investasi dan Klaim Terhadap Laba Pada PT Asuransi Multi Artha Guna Tbk (AMAG). Jurnal Ekonomi Syariah Dan Bisnis, 5(2), 179–192.

Aruan, N. M., Simanjuntak, G. W., & Siagian, A. I. (2023). Pendekatan Algoritma Support Vector Regression Dalam Memprediksi Harga Cryptocurrency (Studi Kasus: Binance). Jurnal Teknik Informatika Dan Sistem Informasi, 10(3). http://jurnal.mdp.ac.id

Atmaja, D. M. U., & Hakim, A. R. (2022). Peramalan Harga Mata Uang Kripto Solana Menggunakan Metode Support Vector Regression (Svr). Jurnal Media Elektro, XI(2), 97–104. https://doi.org/10.35508/jme.v0i0.8117

Baidowi, A., Fitra, E., As, A. H., Tholib, A., & Guterres, J. X. (2024). Implementasi GridSearch dalam Meningkatkan Kinerja Model Support Vector Regression ( SVR ) utuk Prediksi Penjualan Produk pada Meuble Rohman Jaya Implementation of GridSearch to Improve the Performance of the Support Vector Regression ( SVR ) Model for Pr. Keilmuan Dan Aplikasi Teknik Informatika, 3489, 22–30.

Chaidir, R. I. M., Ramadhan, A. F., Zaria, H., & Saputra, R. A. (2024). Perbandingan Algoritma Simple Linear Regression Dan Support Vector Regression Dalam Prediksi Jumlah Penduduk Di Sulawesi Tenggara. METHODIKA: Jurnal Teknik Informatika Dan Sistem Informasi, 10(1), 27–31. https://doi.org/10.46880/mtk.v10i1.2548

E, S. V., Park, J., & Cho, Y. (2020). Using data mining techniques for bike sharing demand prediction in metropolitan city. Computer Communications, 153(February), 353–366. https://doi.org/10.1016/j.comcom.2020.02.007

Fadhillah Rashidatul A’la, Z. F. (2024). Perbandingan Algoritma Decision Tree dan Deep Learning dalam Prediksi Masalah Kesehatan berdasarkan Kebiasaan Gaya Hidup Fadhillah Rashidatul A ’ la , Zaehol Fatah Universitas Ibrahimy , Indonesia lifestyle habits ; health prediction ; decision tree ; dee. Mutiara: Multidiciplinary Scientifict Journal, 2(10).

Fitri, E. (2023). Analisis Perbandingan Metode Regresi Linier, Random Forest Regression dan Gradient Boosted Trees Regression Method untuk Prediksi Harga Rumah. Journal of Applied Computer Science and Technology, 4(1), 58–64. https://doi.org/10.52158/jacost.v4i1.491

Joanda Kaunang, F., Rotikan, R., & Stella Tulung, G. (2018). Pemodelan Sistem Prediksi Tanaman Pangan Menggunakan Algoritma Decision Tree Crop Prediction System Using Decision Tree Algorithm. Cogito Smart Journal, 4(1), 213–218.

Kurniawan, Y., Winoto Tj, H., & Fushen, F. (2022). Pengaruh Kualitas Layanan Dan Penanganan Keluhan Terhadap Loyalitas Pasien BPJS Dimediasi Oleh Kepuasan Pelanggan (Studi Pada Pasien Pengguna BPJS Kesehatan Di RSIA Bunda Sejahtera). Jurnal Manajemen Dan Administrasi Rumah Sakit Indonesia (MARSI), 6(1), 74–85. https://doi.org/10.52643/marsi.v6i1.1939

Mahendra, F., s Siregar, A., & Baihaqi, K. (2024). Implementasi Algoritma Regresi Linear Dan Support Vector Regression Dalam Membuat Model Prediksi Hasil Tangkapan Ikan Nelayan Desa Ciparagejaya. Scientific Student Journal for Information, Technology and Science, 5(1), 9–17.

Murtafiah, N. S., & Hajarisman, N. (2024). Deteksi Anomali Aktivitas Kegempaan Gunung Marapi Menggunakan Algoritma Local Outlier Factor. Bandung Conference Series: Statistics, November 2023, 526–537.

Melati N, R., Waluyo Purboyo, T., & Kalista, M. (2023). Prediksi Penderita Tuberkulosis Menggunakan Algoritma Support Vector Regression (SVR). E-Proceeding of Engineering, 10(1), 736–741.

Pomalingo, S., Sugiantoro, B., & Prayudi, Y. (2019). Data Visualisasi Sebagai Pendukung Investigasi Media Sosial. ILKOM Jurnal Ilmiah, 11(2), 143–151. https://doi.org/10.33096/ilkom.v11i2.443.143-151

Putri, W. E., Buana, U., Karawang, P., Faisal, S., Buana, U., Karawang, P., Rohana, T., Buana, U., & Karawang, P. (2025). Implementasi Algoritma Support Vector Regression dan Polynomial Regression dalam Memprediksi Harga Saham PT Telekomunikasi Indonesia. Scientific Student Journal for Information, Technology and Science, 6, 70–76.

Santika, A., Rahayu, Y., Ernawati, N., & Zuhriatusobah HS, J. (2023). Pengaruh Net Profit Margin, Earning Per Share, Inflasi dan Nilai Tukar Rupiah Terhadap Harga Saham. Owner: Riset & Jurnal Akuntansi, 7(1), 753–763. https://doi.org/10.33395/owner.v7i1.1269

Saputra, R. A., Agustina, C., Puspitasari, D., Ramanda, R., Warjiyono, Pribadi, D., Lisnawanty, & Indriani, K. (2020). Detecting Alzheimer’s Disease by the Decision Tree Methods Based on Particle Swarm Optimization. Journal of Physics: Conference Series, 1641(1), 61–67. https://doi.org/10.1088/1742-6596/1641/1/012025

Septaraja, A. F., Joannes, K., Radhi, M. R., & Parhusip, J. (2024). Implementasi Algoritma Decision Tree Untuk Prediksi Efisiensi Biaya Bensin Kendaraan Bermotor Parenggean Menuju Palangkaraya Implementation Of The Decision Tree Algorithm For Predicting The Cost Efficiency Of Gasoline For Motor Vehicles Parenggean Traveli. Informatech: Jurnal Ilmiah Informatika Dan Komputer, 1, 243–246.

Sinambela, D. P., Naparin, H., Zulfadhilah, M., & Hidayah, N. (2023). Implementasi Algoritma Decision Tree dan Random Forest dalam Prediksi Perdarahan Pascasalin. Jurnal Informasi Dan Teknologi, 5(3), 58–64. https://doi.org/10.60083/jidt.v5i3.393

Sulistiani, H., & Aldino, A. A. (2020). Decision Tree C4.5 Algorithm for Tuition Aid Grant Program Classification (Case Study: Department of Information System, Universitas Teknokrat Indonesia). Edutic - Scientific Journal of Informatics Education, 7(1), 40–50. https://doi.org/10.21107/edutic.v7i1.8849

Wahyuningsih, S., Ediwijoyo, S. P., Ganesha, P. P., & Tengah, J. (2022). Jurnal E-Bis : Ekonomi Bisnis Kajian Prediksi Kebangkrutan Industri Asuransi Di Indonesia Tahun 2019-. E-Bisnis: Ekonomi Bisnis, 6(2), 555–570.

Wardana, F. A., & Juanita, S. (2025). Prediksi jumlah tenaga kerja asing di jawa barat menggunakan perbandingan algoritma support vector regression dan decision tree regression. JIPI (Jurnal Ilmiah Penelitian Dan Pembelajaran Informatika), 10(2), 890–899.