Scholarlink

The life insurance sector depends significantly on risk evaluation to classify applicants. Through the underwriting process, insurers assess applications and establish appropriate pricing for insurance policies. The underwriting process can be automated for quicker application processing due to the growth of data and data analytics developments. This research aims to enhance risk evaluation in the life insurance industry by leveraging predictive analytics. It uses a real-world dataset with over 100 (anonymized) attributes to forecast the applicants’ level of risk with the help of variants of optimizer in the deep learning model. By applying advanced deep learning techniques, this study improves risk prediction accuracy and underwriting efficiency. The model’s optimized algorithms analyze complex datasets, enabling faster, data-driven decisions while maintaining fairness and precision in policy pricing.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Risk Prediction of Life Insurance Applicants Using Optimizer in Deep Neural Network Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Prasanta Baruah,
  • Bijit Das,
  • Biki Majumdar,
  • Nasim Raza,
  • Pankaj Pratap Singh

摘要

The life insurance sector depends significantly on risk evaluation to classify applicants. Through the underwriting process, insurers assess applications and establish appropriate pricing for insurance policies. The underwriting process can be automated for quicker application processing due to the growth of data and data analytics developments. This research aims to enhance risk evaluation in the life insurance industry by leveraging predictive analytics. It uses a real-world dataset with over 100 (anonymized) attributes to forecast the applicants’ level of risk with the help of variants of optimizer in the deep learning model. By applying advanced deep learning techniques, this study improves risk prediction accuracy and underwriting efficiency. The model’s optimized algorithms analyze complex datasets, enabling faster, data-driven decisions while maintaining fairness and precision in policy pricing.