Insurance Reserve Prediction: Opportunities and Challenges

• Published in: 2021 International Conference on Computational Science and Computational Intelligence (CSCI) pp. 290 - 295
• Main Authors: Taha, Ayman, Cosgrave, Bernard, Rashwan, Wael, McKeever, Susan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2021
• Subjects: Actuarial chain ladder; Computer science; Economics; Estimation; Focusing; Insurance; Insurance data analytics; Loss estimation; Prediction methods; Reserve prediction; Scientific computing; Stochastic methods
• DOI: 10.1109/CSCI54926.2021.00120

Predicting claims' reserve is a critical challenge for insurers and has dramatic consequences on their managerial, financial and underwriting decisions. The insurers' capital and their underwriting capacity of further business are impacted by inaccurate reserve estimates. Increasing premium rates and adjusting the underwriting policy decisions may balance the impact of unexpected claims, but will have a negative impact on their business opportunities. To address this, several papers focusing on the prediction of insurance reserve have been published in the literature. In this paper, we provide a comprehensive review of the research on the insurance reserve prediction techniques in economics and actuarial science literature as well as machine learning and computer science literature. Moreover, we classify these techniques into different approaches based on the prediction mechanism they use in estimation. For each approach, we survey reserve prediction methods, and then show the similarities and differences among them. In addition, the review is armed with a discussion on the challenges and the future opportunities.