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 the insurance context. While traditional recommendation systems, designed for online platforms (e.g. e-commerce, videos), are constructed on huge datasets and aim to suggest the next best offer, insurance products have specific properties which imply that we must adopt a different approach. Our recommendation system combines the XGBoost algorithm and the Apriori algorithm to choose which customer should be recommended and which cover to recommend, respectively. It has been tested in a pilot phase of around 150 recommendations, which shows that the approach outperforms standard results for similar up-selling campaigns. Recommendation system Up-selling Car insurance XGBoost algorithm Apriori algorithm

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

“…Conversely, up-selling is another strategic sales tactic in e-commerce that focuses on encouraging customers to consider higher-value or superior-quality alternatives to the items in their cart [10]. By suggesting premium product alternatives, such as an advanced smartphone model with enhanced features, businesses aim to entice customers to spend more [11].…”

Constructing a personalized recommender system for life insurance products with machine‐learning techniques

“…Zeng et al (2015) and Karabadji et al (2018) predicted user ratings with CF and recommended products based on their similarity to other users' ratings and attributes. Desirena et al (2019) and Lesage et al (2020) used data provided by an insurance company to construct recommendation models that assist the company's sales. In prior studies (Qazi et al, 2017(Qazi et al, , 2020, a recommendation model was constructed using a Bayesian network to provide suggestions based on similar customer decisions.…”

“…The insurance industry has also been interested in RA due to the surge in Internet finance (Bi et al, 2020b; Qazi et al, 2020) and the need for personalization (Lesage et al, 2020). Furthermore, the properties of insurance data, in which the products are related to age and personal attributes, have made it seem optimal for recommendation.…”