Menghitung nilai premi asuransi nelayan menggunakan Generalized Linear Model dan Copula

Yanti, Jihan Dwi (2025) Menghitung nilai premi asuransi nelayan menggunakan Generalized Linear Model dan Copula. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text
1_cover.pdf

Download (49kB) | Preview
[img]
Preview
Text
2_abstrak.pdf

Download (93kB) | Preview
[img]
Preview
Text
3_skbebasplariagism.pdf

Download (54kB) | Preview
[img]
Preview
Text
4_daftarisi.pdf

Download (191kB) | Preview
[img]
Preview
Text
5_bab1.pdf

Download (100kB) | Preview
[img] Text
6_bab2.pdf
Restricted to Registered users only

Download (465kB) | Request a copy
[img] Text
7_bab3.pdf
Restricted to Registered users only

Download (541kB) | Request a copy
[img] Text
8_bab4.pdf
Restricted to Registered users only

Download (495kB) | Request a copy
[img] Text
9_bab5.pdf
Restricted to Registered users only

Download (93kB) | Request a copy
[img] Text
10_daftarpustaka.pdf
Restricted to Registered users only

Download (170kB) | Request a copy
[img] Text
11_lampiran.pdf
Restricted to Repository staff only

Download (827kB) | Request a copy

Abstract

Indonesia sebagai negara maritim dengan sektor perikanan yang besar menghadapi tantangan dalam melindungi nelayan dari risiko kecelakaan kerja. Salah satu upaya yang telah dilakukan adalah menyediakan program asuransi nelayan. Namun, penetapan premi yang akurat untuk asuransi ini masih menjadi masalah utama. Penelitian ini mengembangkan model perhitungan premi asuransi nelayan dengan menggabungkan Generalized Linear Model (GLM) dan Copula menggunakan data klaim aktual dari perusahaan asuransi nelayan. Hasil analisis menunjukkan bahwa distribusi Poisson dengan prediktor Jenis Klaim (p < 0.001) dan Usia (p = 0.04) paling sesuai untuk memodelkan frekuensi klaim, sementara distribusi Gamma dengan prediktor Jenis Klaim (p = 0.05) optimal untuk besar klaim. Pemodelan copula berhasil mengukur ketergantungan risiko, dengan hasil simulasi menunjukkan bahwa Gumbel Copula memberikan hasil terbaik dalam simulasi dan menghasilkan estimasi premi yang secara signifikan 15% lebih akurat dibandingkan metode konvensional. Temuan ini tidak hanya memberikan kontribusi metodologis dalam ilmu aktuaria, tetapi juga menawarkan kerangka kerja praktis bagi pengembangan produk asuransi nelayan yang lebih berkelanjutan di Indonesia. Indonesia, as a maritime country with a large fishing sector, faces challenges in protecting fishermen from occupational accident risks. One of the efforts that has been made is to provide a fishermen's insurance program. However, setting accurate premiums for this insurance remains a major issue. This study developed a model for calculating fishermen's insurance premiums by combining the Generalized Linear Model (GLM) and Copula using actual claim data from fishermen's insurance companies. The analysis results indicate that the Poisson distribution with predictors Claim Type (p < 0.001) and Age (p = 0.04) is most suitable for modeling claim frequency, while the Gamma distribution with predictors Claim Type (p = 0.005) is optimal for claim size. Copula modeling successfully quantified risk dependence, with simulation results showing that the Gumbel Copula provided the best results in simulations and produced premium estimates that were significantly 15% more accurate than conventional methods. These findings not only contribute methodologically to actuarial science but also offer a practical framework for the development of more sustainable fishermen's insurance products in Indonesia.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Generalized Linear Model; Copula; Premi Asuransi; Nelayan; Asuransi Nelayan
Subjects: Mathematics
Applied mathematics > Statistical Mathematics
Divisions: Fakultas Sains dan Teknologi > Program Studi Matematika
Depositing User: Jihan Dwi Yanti
Date Deposited: 24 Sep 2025 02:57
Last Modified: 24 Sep 2025 02:57
URI: https://digilib.uinsgd.ac.id/id/eprint/121349

Actions (login required)

View Item View Item