http://repository.president.ac.id/xmlui/handle/123456789/12589 Tue, 07 Apr 2026 12:25:14 GMT 2026-04-07T12:25:14Z http://repository.president.ac.id/xmlui/handle/123456789/12597 ESTIMATION OF IBNR CLAIMS RESERVES USING CHAIN LADDER METHOD AND GENERALIZED LINEAR MODEL (GLM) WITH OVER-DISPERSED POISSON (ODP) DISTRIBUTION Karundeng, Whitney Within the insurance industry, the calculation of reserves for predicting fund allocation becomes highly prominent, as companies must do it accurately to settle future claims. Consequently, insurance firms enhance financial security, ensuring sufficient resources are available to meet obligations, particularly during periods of increased claims activity. This research discusses the calculation of claim reserve estimates using Chain Ladder (CL) method and the Generalized Linear Model (GLM) with Over-Dispersed Poisson (ODP) distribution. Leveraging the simplicity of the CL for baseline projections and the flexibility of GLMs for refining estimates based on additional predictors. Both models yield estimation results for the run-off triangle, illustrating the expected development of claims over a specific period. The case study used in this research involves Auto data from 2010 to 2019 at Zurich Insurance Company in the North America region. The results of calculations using the CL method and GLM with the ODP approach give the same results. Estimates using the ODP approach provide a confidence interval between USD 1,479,610 and USD 1,480,253. The prediction error with MAPE results is the same for both CL and GLM method which is 42,81%. Based on these results, it can be concluded that insurance companies can use the GLM method as a method that provides confidence intervals for making insurance decisions in providing claims reserves. Mon, 01 Jan 2024 00:00:00 GMT http://repository.president.ac.id/xmlui/handle/123456789/12597 2024-01-01T00:00:00Z http://repository.president.ac.id/xmlui/handle/123456789/12596 FINITE DIFFERENCE METHOD FOR SOLVING BLACK- SCHOLES EQUATION IN EUROPEAN OPTION Ningtyas, Irmadella Puspita Option pricing is one of the most important concerns in the world of finance. An option is an agreement between two parties to buy or sell an asset at a certain strike price in the future. Option can be classified into two types based on the sort of rights possessed by the holder, which are Call Option and Put Option. One method for calculating the option value is to use the Black Scholes model. Analytically resolving this equation can be difficult, particularly for more complicated option and market circumstances. One method that can be used in such situations is the finite difference method. This technique offers numerical solutions for option under actual market conditions and enables the computation of increasingly complex option values. This study aims to determine the option price using the explicit finite difference method applied to Tesla company stock price data. The results obtained from the explicit finite difference method will then be compared with the analytical method calculated using the Black-Scholes model. The analysis of the Black-Scholes equation using the explicit finite difference method highlights its performance and stability across different time steps. Using a grid partition of = = 5, the method closely approximates the analytical values at = 0.2, resulting in minimal error with 0.0189 at = 300 for both Call and Put Option with mean of the error analysis are 1.0014 for Call Option and 0.2080 for Put Option. But the result significantly deviates at = 1 for both Call and Put Option. Leading to the largest error with 24.7095 at = 120 and the mean of the error analysis is 13.0183 for the Call Option. And for the Put Option, the largest error is 16.2287 at = 60 and the mean of the error analysis is 6.2927. This result consistent for both call and put options reinforce these findings, indicating that while the explicit finite difference method provides accurate approximations at earlier time steps. Mon, 01 Jan 2024 00:00:00 GMT http://repository.president.ac.id/xmlui/handle/123456789/12596 2024-01-01T00:00:00Z http://repository.president.ac.id/xmlui/handle/123456789/12595 CALCULATION OF RUIN PROBABILITY IN THE CLASSICAL RISK PROCESS WITH WEIBULL AND PARETO CLAIM DISTRIBUTION Fauziyah, Nur Fani The Weibull and Pareto distributions are commonly used in the insurance industry because they effectively model different aspects of risk and loss also their ability to model a wide range of risk case effectively. The calculation of ruin probability can be used to estimate and anticipate insurance companies from bankruptcy. One of the models to calculate ruin probability is classical risk process, in classical risk process a company considered bankrupt when the surplus process falls to zero or below. In this thesis, the calculation of ruin probability will calculated through survival probability using numerical approximations that is Euler’s method and Trapezoidal rule. The claim data from vehicle insurance be assumed to be Weibull and Pareto distributed and to get the maximum parameter value will use the Maximum Likelihood Estimation method. The result show the Pareto distribution yields a higher ruin probability compared to the Weibull distribution Mon, 01 Jan 2024 00:00:00 GMT http://repository.president.ac.id/xmlui/handle/123456789/12595 2024-01-01T00:00:00Z http://repository.president.ac.id/xmlui/handle/123456789/12594 COMPARISON OF MAXIMUM LIKELIHOOD ESTIMATION AND METHOD OF MOMENTS FOR ESTIMATING PARETO DISTRIBUTION PARAMETERS ON MEDICAL MALPRACTICE CLAIMS Simanjuntak, Erika Prischilia Medical Malpractice Claims present unique challenges for healthcare providers and insurance carriers because of their uncertain nature. Large financial losses arising from a high claim count are difficult to quantify. Therefore, an appropriate distribution model and estimation method are essential for effective risk management and planning. One of the significant distribution models is Pareto Distribution, having estimation techniques such as Maximum Likelihood Estimation (MLE) and Method of Moments (MoM). The objective of this study is to investigate the potential performance disparity between two major types of methods that is Maximum Likelihood Estimation and Method of Moments for estimating Pareto distribution parameters on medical malpractice claims data as applied specifically to the frequency-of-claims problem, focusing particularly on claim ages falling within age interval 36–65 years. The evaluation is done based on error metrics that is Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The analysis results show that MAE value for MoM is 0.02065, while for MLE is 0.01883. The MAPE calculation results show that the prediction value of MoM is 63%, while that of the MLE is 57%. In addition, the MSE value for MoM is 0.00060 and for the MLE is 0.00047. Last, the RMSE value for MoM is 0.02440, while for the MLE is 0.02163. Furthermore, the MAPE exceeding 50% indicates both methods are less effective for this particular case. However, based on the MAE, MSE, and RMSE results in this study, MLE and MoM show almost the same accuracy, so both methods can be considered equally good for parameter estimation. Nonetheless, in general, MLE is often considered a better method than MoM due to its more comprehensive approach in theory. Mon, 01 Jan 2024 00:00:00 GMT http://repository.president.ac.id/xmlui/handle/123456789/12594 2024-01-01T00:00:00Z