<xml> </xml><![endif]--><!--[if gte mso 9]><xml> Normal 0 false false false EN-US X-NONE X-NONE </xml><![endif]--><!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 10]> <style> /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:8.0pt; mso-para-margin-left:0in; line-height:107%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;} </style> <![endif]-->In order to maintain financial stability and fulfill obligations to policyholders, insurance companies need to allocate claim reserves accurately. This study aims to conduct a comparative analysis of claim reserving methods between conventional approaches and the bootstrap method on Chain Ladder, Bornhuetter Ferguson, Cape Cod, and Double Chain Ladder. It also calculates the best estimate liabilities and risk adjustments in accordance with IFRS 17 standards. In the first case study, six datasets were utilized, each representing a different line of business (LOB). The analysis results indicate that no single method can be universally deemed ”best” for estimating claim reserves. This is evidenced by the comparison of error indicator metrics across methods, showing that a method with the lowest error for one LOB does not necessarily yield the lowest claim reserve error when applied to another LOB. In the second case study, which used datasets comprising frequency and severity data, a comparison of predictive error values was conducted between the bootstrap CL and bootstrap DCL methods. The results show that the predictive error of the bootstrap DCL method (10%) is lower than that of the bootstrap CL method (13%). In the analysis of best estimate liabilities and risk adjustments, it was found that the risk adjustment values in the bootstrap BF method were consistently lower than those in the bootstrap CL method. This is due to the use of a prior estimator, ?, which makes the values in the bootstrap BF method more stable."> <xml> </xml><![endif]--><!--[if gte mso 9]><xml> Normal 0 false false false EN-US X-NONE X-NONE </xml><![endif]--><!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 10]> <style> /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:8.0pt; mso-para-margin-left:0in; line-height:107%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;} </style> <![endif]-->In order to maintain financial stability and fulfill obligations to policyholders, insurance companies need to allocate claim reserves accurately. This study aims to conduct a comparative analysis of claim reserving methods between conventional approaches and the bootstrap method on Chain Ladder, Bornhuetter Ferguson, Cape Cod, and Double Chain Ladder. It also calculates the best estimate liabilities and risk adjustments in accordance with IFRS 17 standards. In the first case study, six datasets were utilized, each representing a different line of business (LOB). The analysis results indicate that no single method can be universally deemed ”best” for estimating claim reserves. This is evidenced by the comparison of error indicator metrics across methods, showing that a method with the lowest error for one LOB does not necessarily yield the lowest claim reserve error when applied to another LOB. In the second case study, which used datasets comprising frequency and severity data, a comparison of predictive error values was conducted between the bootstrap CL and bootstrap DCL methods. The results show that the predictive error of the bootstrap DCL method (10%) is lower than that of the bootstrap CL method (13%). In the analysis of best estimate liabilities and risk adjustments, it was found that the risk adjustment values in the bootstrap BF method were consistently lower than those in the bootstrap CL method. This is due to the use of a prior estimator, ?, which makes the values in the bootstrap BF method more stable.">
Laporkan Masalah

PREDIKSI CADANGAN KLAIM RBNS DAN IBNR DENGAN PENGAPLIKASIAN BOOTSTRAP DAN IMPLEMENTASINYA PADA NILAI ESTIMASI LIABILITAS TERBAIK SERTA PENYESUAIAN RISIKO IFRS 17

Jason Putra Wirjo Santoso, Dr. Solikhatun, S.Si., M.Si.

2025 | Skripsi | S1 ILMU AKTUARIA

<!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 9]><xml> Normal 0 false false false EN-US X-NONE X-NONE </xml><![endif]--><!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 10]> <style> /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:8.0pt; mso-para-margin-left:0in; line-height:107%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;} </style> <![endif]-->

Dalam rangka menjaga stabilitas keuangan dan memenuhi kewajiban kepada nasabah, Perusahaan asuransi perlu mengalokasikan cadangan klaim secara akurat. Penelitian ini bertujuan untuk melakukan analisis komparatif metode claim reserving antara metode konvensional dengan metode bootstrap pada Chain Ladder, Bornhuetter Ferguson, Cape Cod, Double Chain Ladder, dan melakukan perhitungan terhadap nilai estimasi liabilitas terbaik serta penyesuaian risiko sesuai dengan standar IFRS 17. Pada bagian studi kasus pertama, digunakan enam dataset yang masing-masing merepresentasikan LOB yang berbeda. Hasil analisis menunjukkan bahwa tidak ditemukan satu metode yang dapat dikatakan ”terbaik” secara universal dalam mengestimasi cadangan klaim. Hal ini dibuktikan melalui nilai matriks indikator perbandingan tingkat error antar metode yang mana menunjukkan bahwa ketika satu metode yang memiliki nilai error terendah di satu LOB belum tentu menghasilkan nilai estimasi cadangan klaim dengan nilai error terendah ketika diimplementasikan di LOB lainnya. Pada bagian studi kasus kedua, di mana dataset yang digunakan terdiri dari data frequency dan severity, dilakukan perbandingan nilai predictive error antara metode bootstrap CL dengan bootstrap DCL. Hasil yang diperoleh menunjukkan nilai predictive error dari metode bootstrap DCL (10%) lebih rendah dibandingkan metode bootstrap CL (13%). Pada bagian analisis nilai estimasi liabilitas terbaik dan penyesuaian risiko, diperoleh bahwa nilai penyesuaian risiko pada metode bootstrap BF selalu lebih kecil dibandingkan dengan metode bootstrap CL. Hal ini disebabkan adanya penggunaan prior estimator berupa ? yang menyebabkan nilai pada metode bootstrap BF menjadi lebih stabil.

<!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 9]><xml> Normal 0 false false false EN-US X-NONE X-NONE </xml><![endif]--><!--[if gte mso 9]><xml> </xml><![endif]--><!--[if gte mso 10]> <style> /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:8.0pt; mso-para-margin-left:0in; line-height:107%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;} </style> <![endif]-->In order to maintain financial stability and fulfill obligations to policyholders, insurance companies need to allocate claim reserves accurately. This study aims to conduct a comparative analysis of claim reserving methods between conventional approaches and the bootstrap method on Chain Ladder, Bornhuetter Ferguson, Cape Cod, and Double Chain Ladder. It also calculates the best estimate liabilities and risk adjustments in accordance with IFRS 17 standards. In the first case study, six datasets were utilized, each representing a different line of business (LOB). The analysis results indicate that no single method can be universally deemed ”best” for estimating claim reserves. This is evidenced by the comparison of error indicator metrics across methods, showing that a method with the lowest error for one LOB does not necessarily yield the lowest claim reserve error when applied to another LOB. In the second case study, which used datasets comprising frequency and severity data, a comparison of predictive error values was conducted between the bootstrap CL and bootstrap DCL methods. The results show that the predictive error of the bootstrap DCL method (10%) is lower than that of the bootstrap CL method (13%). In the analysis of best estimate liabilities and risk adjustments, it was found that the risk adjustment values in the bootstrap BF method were consistently lower than those in the bootstrap CL method. This is due to the use of a prior estimator, ?, which makes the values in the bootstrap BF method more stable.

Kata Kunci : Bootstrap, Chain Ladder, Bornhuetter-Ferguson, Cape Cod, Double Chain Ladder, IFRS 17, estimasi liabilitas terbaik, penyesuaian risiko

  1. S1-2025-477310-abstract.pdf  
  2. S1-2025-477310-bibliography.pdf  
  3. S1-2025-477310-tableofcontent.pdf  
  4. S1-2025-477310-title.pdf