A Recommendation System For Car Insurance

Abstract : We construct a recommendation system for car insurance, to allow agents to optimize up-selling performances, by selecting customers who are most likely to subscribe an additional cover. The originality of our recommendation system is to be suited for insurance context. While traditional recommendation systems, designed for online platforms (e.g. e-commerce, videos), are constructed on huge data-sets and aim to suggest the next best offer, insurance products have specific properties which imply to adopt a different approach. Our recommendation system combines XGBoost algorithm and Apriori algorithm to choose which customer should be recommended and which cover to recommend, respectively. It has been tested in a pilot phase of hundreds of recommendations, which shows that the approach outperforms standard results for similar up-selling campaigns. Recommendation system Up-selling Car insurance XGBoost algorithm Apriori algorithm
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-02420954
Contributor : Antoine Lejay <>
Submitted on : Friday, December 20, 2019 - 11:01:51 AM
Last modification on : Monday, January 13, 2020 - 1:19:06 AM

File

car_recommandation_R0.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02420954, version 1

Collections

Citation

Laurent Lesage, Madalina Deaconu, Antoine Lejay, Jorge Meira, Geoffrey Nichil, et al.. A Recommendation System For Car Insurance. 2019. ⟨hal-02420954⟩

Share

Metrics

Record views

31

Files downloads

132