Bayesian Learning with Forgetting: An Empirical Analysis of Automobile Insurance Policyholders

76 Pages Posted: 1 May 2024

See all articles by Chao Ma

Chao Ma

WISE & SOE, Xiamen University

Date Written: October 1, 2021

Abstract

Analyzing data from a Chinese automobile insurance company, we find that policyholders’ past accident experience reduces their accident probabilities in the current period. Our explanation is that accidents make policyholders update their beliefs about their innate risk types upward and hence exert more caution. The Chinese additive “bonus-malus” scheme helps rule out changes in financial incentives as an alternative explanation. Additionally, we find that the magnitude of negative effect of a past accident is smaller if the accident occurred longer ago, suggesting a forgetting effect in the learning process. Structural estimations show that the monthly forgetting rate is 0.1385.

Keywords: learning, forgetting, information asymmetry, automobile insurance, car accidents, adverse selection, moral hazard

JEL Classification: D81, D82, D83, D9, L8, G22, G4, G52, R41

Suggested Citation

Ma, Chao, Bayesian Learning with Forgetting: An Empirical Analysis of Automobile Insurance Policyholders (October 1, 2021). Available at SSRN: https://ssrn.com/abstract=4813892 or http://dx.doi.org/10.2139/ssrn.4813892

Chao Ma (Contact Author)

WISE & SOE, Xiamen University ( email )

A 307, Economics Building
Xiamen, Fujian 10246
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
10
Abstract Views
64
PlumX Metrics