Leveraging Artificial Intelligence Algorithms for Risk Prediction in Life Insurance Service Industry

Citation: Srikanth Reddy Vangala, Ram Mohan Polam, Bhavana Kamarthapu, Ajay Babu Kakani, Sri Krishna Kireeti Nandiraju, Sandeep Kumar Chundru, "Leveraging Artificial Intelligence Algorithms for Risk Prediction in Life Insurance Service Industry", Universal Library of Engineering Technology, Special Issue.

Copyright: This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Accurate risk prediction is essential in the life insurance industry to enhance underwriting processes and detect fraudulent activities effectively. This paper suggests a model for healthcare insurance fraud detection and risk assessment using an Artificial Neural Network (ANN) applied to the Prudential Insurance dataset. Data cleaning, categorical variable encoding, and resolving class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) are all part of the extensive preparation that the dataset goes through in order to optimize model learning. Our ANN model has been trained and tested using industry-standard regression metrics, and it has achieved impressive results: R²= 92.7%, MAE= 14.3%, MSE= 72.7, and RMSE= 27. These outcomes prove that the model is strong and can correctly identify complicated nonlinear relationships in the data, which greatly improves the accuracy of risk predictions. The findings suggest that the proposed ANN model is a powerful tool for life insurance providers to optimize underwriting, improve fraud detection accuracy, and deliver personalized insurance products.

Keywords: Healthcare Insurance, Artificial Neural Network (ANN), Prudential Insurance Dataset, Risk Prediction, Life Insurance.

https://doi.org/10.70315/uloap.ulete.2022.004