Perbandingan Metode Hybrid SARIMA-LSTM Dan Holt-Winters Untuk Peramalan Kontribusi Bruto Dan Klaim Bruto Asuransi Jiwa Syariah Di Indonesia

Alim, Alfan (2025) Perbandingan Metode Hybrid SARIMA-LSTM Dan Holt-Winters Untuk Peramalan Kontribusi Bruto Dan Klaim Bruto Asuransi Jiwa Syariah Di Indonesia. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5006211014-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Industri asuransi jiwa syariah memegang peranan penting dalam perekonomian Indonesia, terutama dalam menyediakan perlindungan finansial berbasis prinsip syariah dan mendukung stabilitas ekonomi nasional. Namun, tantangan seperti meningkatnya rasio klaim berpotensi mengganggu kesehatan keuangan dan keberlanjutan operasional industri. Penelitian ini bertujuan untuk membandingkan kinerja dua metode peramalan, yaitu Holt-Winters dan hybrid SARIMA-LSTM, dalam memproyeksikan kontribusi bruto dan klaim bruto asuransi jiwa syariah di Indonesia. Data yang digunakan mencakup periode Januari 2014 hingga Februari 2025. Metode Holt-Winters efektif dalam menangkap pola musiman, tren, dan level data, sedangkan hybrid SARIMA-LSTM menggabungkan kekuatan model linier SARIMA dan kemampuan LSTM dalam mendeteksi pola non-linear. Hasil penelitian menunjukkan bahwa Holt-Winters memberikan akurasi terbaik dalam memproyeksikan kontribusi bruto dengan nilai MAPE sebesar 7,9579%, sementara hybrid SARIMA(0,1,0)(2,1,0)[12]-LSTM (4,1,1) lebih unggul dalam memprediksi klaim bruto dengan MAPE sebesar 3,2675%. Selain itu, hasil perhitungan rasio klaim bruto yang diperoleh dari peramalan kontribusi dan klaim bruto menunjukkan tren peningkatan signifikan, dari 84,48% hingga 128,54% pada Desember 2025, mencerminkan bahwa klaim diperkirakan melampaui kontribusi. Temuan ini diharapkan menjadi dasar strategis bagi perusahaan asuransi jiwa syariah dalam mengevaluasi kecukupan kontribusi, memperketat kebijakan underwriting, mengoptimalkan reasuransi, dan menyusun proyeksi keuangan jangka menengah hingga panjang secara lebih akurat demi menjaga kesehatan dana peserta dan stabilitas industri.
=================================================================================================================================
The Sharia life insurance industry plays an important role in Indonesia’s economy, especially in providing financial protection based on Sharia principles and supporting national economic stability. However, challenges such as the rising claim ratio have the potential to disrupt financial health and the sustainability of the industry’s operations. This study aims to compare the performance of two forecasting methods, namely Holt-Winters and hybrid SARIMA-LSTM, in projecting gross contribution and gross claims of Sharia life insurance in Indonesia. The data used covers the period from January 2014 to February 2025. The Holt-Winters method is effective in capturing seasonal patterns, trends, and data levels, while the hybrid SARIMA-LSTM combines the strength of the linear SARIMA model with the capability of LSTM to detect non-linear patterns. The results show that Holt-Winters provides the best accuracy in projecting gross contribution, with a MAPE value of 7,9579%, while the hybrid SARIMA(0,1,0)(2,1,0)[12]-LSTM (4,1,1) performs better in predicting gross claims with a MAPE of 3,2675%. In addition, the calculated gross claim ratio based on the forecasted gross contribution and claims shows a significant increasing trend, from 84,48% to 128,54% by December 2025, indicating that claims are expected to exceed contributions. These findings are expected to serve as a strategic foundation for Sharia life insurance companies in evaluating contribution adequacy, tightening underwriting policies, optimizing reinsurance, and preparing more accurate medium to long term financial projections to maintain fund health and industry stability.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Hybrid SARIMA-LSTM, Holt-Winters, Klaim Bruto, Kontribusi Bruto, Peramalan, Rasio Klaim, Claims Ratio, Forecasting, Gross Claims, Gross Contribution, Holt-Winters, Hybrid SARIMA-LSTM.
Subjects:	H Social Sciences > H Social Sciences (General) > H61.4 Forecasting in the social sciences H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HD Industries. Land use. Labor > HD30.27 Business forecasting H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management Q Science T Technology > T Technology (General)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User:	Alfan Alim
Date Deposited:	14 Jul 2025 03:40
Last Modified:	14 Jul 2025 03:40
URI:	http://repository.its.ac.id/id/eprint/119666

Actions (login required)

View Item