Prediksi Klaim Asuransi Perjalanan Menggunakan Machine Learning untuk Optimasi Manajemen Risiko

Travel insurance provides financial protection for individuals during their trips, both domestically and internationally. With the increasing demand for travel insurance, insurance companies face challenges in efficiently managing claims. This study aims to develop a predictive model to classify whether an insurance policy will be claimed based on historical customer and transaction data. This research utilizes a dataset containing various features related to travel and policyholders, such as agent type, distribution channel, insurance product, travel duration, and premium amount. The methods used include data exploration, feature processing, and the application of machine learning algorithms such as Logistic Regression, Random Forest, and XGBoost. Experimental results indicate that the XGBoost model performs the best, achieving the highest accuracy compared to other models. With this predictive model, insurance companies can optimize claim evaluation processes, reduce fraud risks, and improve operational efficiency in handling travel insurance claims.