Pemodelan Prediksi Status Keberlanjutan Polis Asuransi Kendaraan dengan Teknik Pemilihan Mayoritas Menggunakan Algoritma-Algoritma Klasifikasi Data Mining
Keywords:
data mining 1, prediksi keberlanjutan polis asuransi kendaraan 2, majority voting 3, algoritma klasifikasi 4Abstract
Motor vehicle insurance is a type of business that covers loss or risk of damage that can arise from various potential events that happen to vehicles. Competition in the insurance business, especially for motorized vehicles, demands innovation and strategies to guarantee business continuity. One of the efforts that companies can make is to predict vehicle insurance policies' sustainability status by analyzing customer profile and transaction data. Prediction of the policyholder's decision is essential for the company because it can determine the marketing strategy that influences its decision to renew the insurance policy. This study has proposed a prediction model for vehicle insurance policies' sustainability status with the majority selection technique from the classification results using data mining algorithms such as Naive Bayes, Support Vector Machine, and Decision Tree. The test results using the confusion matrix show that the best accuracy value is obtained at 93.57%, whatever for the precision value reaches 97.20%, and the recall value is 95.20%, and the F-Measure value is 95.30%. The best model evaluation scores are generated using the majority voting approach, outperforming a single classifier-based prediction model's performance.
Downloads
References
Bustami, “Penerapan Algoritma Naive Bayes Untuk Mengklasifikasi Data Nasabah Asuransi,” Jurnal Informatika, vol. 8, no. 1, hal.
–898, 2014.
Betrisandi, “Klasifikasi Nasabah Asuransi Jiwa Menggunakan Algoritma Naive Bayes Berbasis Backward Elimination,” ILKOM Jurnal Ilmiah, vol. 9, no. 1, hal. 96–101, 2017.
R. Sutitis, S. Suparti, dan D. Ispriyanti, “Klasifikasi Tingkat Kelancaran Nasabah Dalam Membayar Premi Dengan Menggunakan Metode Regresi Logistik Ordinal Dan Naãve Bayes,” Jurnal Gaussian, vol. 4, no. 3, hal. 651–659, 2015.
W. F. Pattipeilohy, A. Wibowo, dan D. R. Utari, “Fakultas Teknik – Universitas Muria Kudus,” in Prosiding SNATIF ke-4 Tahun 2017, 2017, hal. 96–101.
A. Alhamad, A. I. S. Azis, B. Santoso, dan S. Taliki, “Prediksi Penyakit Jantung Menggunakan Metode-Metode Machine
Learning Berbasis Ensemble – Weighted Vote,”Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 5, no. 3, hal. 352, 2019.
Kusrini, Algoritma Data Mining. Jakarta, 2009.
R. T. Wulandari, Data Mining Teori dan Aplikasi Rapidminer. 2017.
A. S. Nugroho, “Pengantar Support Vector Machine,” 2007, hal. 1–6.
M. Windarti dan A. Suradi, “Perbandingan Kinerja 6 Algoritme Klasifikasi Data Mining untuk Prediksi Masa Studi Mahasiswa,” Telematika, vol. 12, no. 1, hal. 14, 2019.
I. G. A. Suwartane, M. Syafrullah, dan K. Adiyarta, “Prediction models of diabetes diseases based on Heterogeneous Multiple Classifiers,” International Journal of Advances in Soft Computing and its Applications, vol. 10, no. 2, hal. 33–49, 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Prosiding Seminar Nasional Teknoka
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.