Stochastic reserving with a stacked model based on a hybridized Artificial Neural Network
作者：
Highlights：
• Stacking models leads to a more accurate estimation of general insurance reserves.
• Risk measurements precision is increased by stacking algorithms and reserving models.
• Machine learning improves Chain Ladder and Bayesian models when they are all combined.
• Merging Neural Networks with other models leads to a more adequate stochastic reserve.
摘要
•Stacking models leads to a more accurate estimation of general insurance reserves.•Risk measurements precision is increased by stacking algorithms and reserving models.•Machine learning improves Chain Ladder and Bayesian models when they are all combined.•Merging Neural Networks with other models leads to a more adequate stochastic reserve.
论文关键词：Stochastic reserving,Reserving risk,Machine learning,General insurance,Run-off prediction
论文评审过程：Received 18 September 2019, Revised 17 July 2020, Accepted 18 July 2020, Available online 3 August 2020, Version of Record 11 August 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113782
