IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Actuaria
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Actuaria
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penerapan Model Kredibilitas Bühlmann–Straub dengan Pendekatan Segmentasi Risiko dalam Penentuan Premi Asuransi Pertanian

      Thumbnail
      View/Open
      Cover (430.9Kb)
      Fulltext (866.1Kb)
      Lampiran (674.5Kb)
      Date
      2026
      Author
      Senjaya, Davin
      Setiawaty, Berlian
      Metadata
      Show full item record
      Abstract
      Kelapa sawit merupakan komoditas strategis Indonesia dengan nilai ekspor mencapai 23,8 miliar dolar Amerika Serikat pada tahun 2023, namun produktivitasnya rentan terhadap risiko iklim, hama, dan fluktuasi harga. Penelitian ini bertujuan menentukan premi asuransi pertanian komoditas kelapa sawit menggunakan model kredibilitas Bühlmann–Straub (BS) dengan pendekatan segmentasi risiko berbasis clustering. Data yang digunakan adalah data produksi dan luas panen kelapa sawit dari 20 provinsi Indonesia periode 2005–2023 yang bersumber dari Badan Pusat Statistik. Loss cost ratio (LCR) dihitung sebagai variabel risiko utama menggunakan nilai actual production history (APH). Pengelompokan provinsi dilakukan menggunakan hierarchical clustering metode Ward berdasarkan rata-rata LCR, menghasilkan tiga cluster dengan karakteristik risiko rendah, menengah, dan tinggi. Pemilihan sebaran terbaik menggunakan uji Kolmogorov–Smirnov dan nilai Akaike information criterion menunjukkan sebaran eksponensial sesuai untuk data overall, cluster I, dan cluster III, sedangkan sebaran Weibull sesuai untuk cluster II. Premi kredibilitas dihitung melalui tiga skenario model BS. Model tanpa segmentasi menghasilkan premi kredibilitas dengan rata-rata 0,0643, sedangkan model dengan segmentasi pada level provinsi menghasilkan diferensiasi premi yang lebih proporsional terhadap profil risiko masing-masing wilayah. Hasil menunjukkan bahwa segmentasi risiko menghasilkan premi kredibilitas yang lebih adil dibandingkan dengan pendekatan overall.
       
      Palm oil is one of Indonesia's strategic commodities with export values reaching USD 23.8 billion in 2023. However, palm oil production, remains vulnerable to climate risk, infestation, and price fluctuations. This study aims to determine agricultural insurance premiums for palm oil using the Bühlmann–Straub (BS) credibility model combined with a clustering-based risk segmentation approach. The study utilizes data on palm oil production and harvested area from 20 Indonesian provinces during the 2005–2023 period, obtained from Statistics Indonesia. The loss cost ratio (LCR), calculated is used as the primary risk variable. Using Actual Production History (APH) values, provincial grouping is performed using Ward's hierarchical clustering method based on mean LCR values, resulting in three clusters representing low, medium, and high-risk characteristics. The Bestfitting probability are selected using the Kolmogorov–Smirnov test and Akaike information criterion. The results indicate that the exponential distribution provides the best fit for the overall dataset as well as for cluster I and cluster III, while the Weibull distribution is most appropriate for cluster II. Credibility premiums are then calculated under three BS model scenarios. The unsegmented model produced an average credibility premium of 0.0643, whereas the province-level segmentation approach yields premiums, that are more proportional to the risk characteristics of each region. These findings suggest that risk segmentation generates fairer and more representative credibility premium estimates than the overall modelling approach.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/173515
      Collections
      • UF - Actuaria [99]

      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