Optimizing Life Insurance Portfolio Management in Egypt through AI-Powered Prediction of Policy Lapses and Cancellations

نوع المستند : المقالة الأصلية

المؤلفون

1 قسم التأمين والعلوم الاكتوارية، كلية التجارة، جامعة بنها

2 قسم التأمين والعلوم الاكتوارية، كلية التجارة، جامعة القاهرة

المستخلص

Policy lapses and cancellations pose significant challenges to the stability and profitability of the Egyptian insurance market. This study evaluates the effectiveness of machine learning (ML) models—Logistic Regression, Random Forest, Support Vector Machines (SVM), and Artificial Neural Networks (ANN)—to predict lapses based on policyholder data and behavioral trends. Key predictors such as income, age, premium amount, payment frequency, and policy type were analyzed to identify actionable insights. The findings highlight the transformative potential of AI in improving customer retention, optimizing operational efficiency, and addressing critical market challenges.
The findings demonstrate that AI-based predictive models offer significant improvements in forecasting policy lapses and cancellations compared to traditional methods. These models effectively capture complex, non-linear relationships within the data, resulting in more accurate and reliable predictions. The study emphasizes the importance of using advanced data preprocessing, feature engineering, and model evaluation techniques to ensure optimal model performance.
Furthermore, the research underscores the importance of predictive analytics in reducing the financial impact of policy lapses and cancellations. By identifying at-risk policies in advance, insurance companies can take proactive measures, such as targeted marketing and personalized interventions, to retain valuable customers and improve overall profitability.

الكلمات الرئيسية

مجلة البحوث المالية والتجارية
المجلد 26، العدد 2 - الرقم المسلسل للعدد 1
الجزء الأول: أبحاث متخصصة في الاقتصاد والاحصاءوالعلوم السياسية
إبريل 2025
الصفحة 391-421

ملفات

شارك

إرسال الاستشهاد إلى

الإحصائيات