Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Eksponensial
Rinaldi, Rival
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Mathematics Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penerapan Metode Klasifikasi Multinomial Naive Bayes Rinaldi, Rival; Goejantoro, Rito; Syaripuddin, Syaripuddin
EKSPONENSIAL Vol 12 No 2 (2021)
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.473 KB) | DOI: 10.30872/eksponensial.v12i2.803

Abstract

Life insurance is a risk management service provide payment to policyholders in the event of a disaster that has been stipulated in the agreement. A classification system needs to be done to facilitate the company in making decisions to provide policies to customers. One system that can be used is multinomial Naive Bayes. Multinomial Naive Bayes is a simple probabilistic classification that has more than two groups or categories. An algorithm using Bayes theorem assumes all independent variables. The aim of this study is to obtain an accuracy level of 5 different proportions with the Naive Bayes multinomial method used in insurance customer payment status data. The data used is the customer data of PT. Prudential Life Samarinda in 2019 with the status of current premium payment, substandard and non-current and using 5 independent variables, namely income, age, amount of premium payment, sex and employment. The results of the measurement of classification accuracy using APER status premium payment on insurance customer data of PT. Prudential Life 2019 Naive Bayes multinomial method showed 22,96% misclassification at 50:50 proportion, at the proportion of 60:40 there were 21,43% misclassification, at the proportion of 70:30 there were 19,05% misclassified, at proportions 80:20 had a misclassification of 14,29%, and a proportion of 90:10 has a misclassification of 7,14%.
Co-Authors Rito Goejantoro, Rito Syaripuddin Syaripuddin