View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Actuaria
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Actuaria
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Analisis Clustering Menggunakan Metode K-Modes dan Pemodelan Frekuensi Klaim pada Asuransi Kendaraan Bermotor

      Thumbnail
      View/Open
      Cover (2.232Mb)
      Fulltext (9.520Mb)
      Lampiran (993.3Kb)
      Date
      2024
      Author
      Firdaus, Farah
      Budiarti, Retno
      Septyanto, Fendy
      Metadata
      Show full item record
      Abstract
      Banyak masyarakat yang semakin sadar akan risiko, sehingga penggunaan asuransi bermotor banyak diminati sebagai langkah pencegahan. Penelitian ini bertujuan untuk mengelompokkan pelanggan asuransi kendaraan bermotor menggunakan metode k-modes clustering pada data kategorik dengan jarak simple matching. Hasil yang didapatkan yaitu terbentuk tiga cluster yang divalidasi melalui metode elbow dan Davies-Bouldin Index (DBI). Setelah dilakukan clustering, tahap selanjutnya menganalisis faktor-faktor yang memengaruhi frekuensi klaim dalam setiap cluster yang terbentuk dengan pemodelan regresi. Cluster 1 dimodelkan dengan regresi logistik binomial, sedangkan cluster 2 dan cluster 3 dimodelkan dengan regresi binomial negatif sesuai dengan distribusi data masing-masing. Hasil analisis menunjukkan bahwa pada cluster 2, terdapat lima variabel yang signifikan memengaruhi frekuensi klaim. Sementara itu, pada cluster 1 dan 3 terdapat enam variabel yang memengaruhi frekuensi klaim.
       
      As more and more people become aware of the risks, motor vehicle insurance is increasingly popular as a preventive measure. In this study, classify motor vehicles insurance customers using the k-modes clustering method on category data with simple matching distance. The results indicate the formation of three clusters, validated through the elbow method and the Davies-Bouldin Index (DBI). After clustering, the next step is to analyze the factors that influence the frequency of claims in each cluster using regression modeling. Cluster 1 was modeled with binomial logistic regression, while cluster 2 and cluster 3 were modeled with negative binomial regression, according to the distribution of each dataset. The analysis results show that in cluster 2, five variables significantly affect claim frequency. Meanwhile, in clusters 1 and 3, six variables influence claim frequency.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/160113
      Collections
      • UT - Actuaria [205]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository