Personalized Health Insurance Recommendation with Retrieval-Augmented Generation: A Study of Lexical, Dense, and Hybrid Retrieval

Simple item page
dc.contributor.authorRujireksareekul, Phakon
dc.contributor.authorAnuntachai, Anuntapat
dc.contributor.authorNetisopakul, Ponrudee
dc.date.accessioned2026-08-06T10:55:53Z
dc.date.available2026-08-06T10:55:53Z
dc.date.issued2026-06-16
dc.description.abstractHealth insurance information in Thailand is available on many company websites and is presented in different formats, making it difficult for users to compare coverage, conditions, and benefits. In this study, we propose a personalized health insurance recommendation system using Retrieval-Augmented Generation (RAG). The system retrieves information using three methods: BM25, dense retrieval, and hybrid retrieval with Reciprocal Rank Fusion. The language model analyzes the retrieved insurance plans and recommends suitable options based on the user query. Experimental results show that dense retrieval provides the best overall performance, while hybrid retrieval performs better than lexical search. The proposed RAG system also maintains practical response latency, making it suitable for interactive applications.
dc.identifier.citationIait 2026 14th International Conference on Advances in Information Technology, 2026
dc.identifier.doi10.1145/3816713.3818802
dc.identifier.other2-s2.0-105045298914
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/18197
dc.sourceIait 2026 14th International Conference on Advances in Information Technology
dc.subjectBM25
dc.subjectdense retrieval
dc.subjecthealth insurance
dc.subjecthybrid retrieval
dc.subjectpersonalized recommendation
dc.subjectreciprocal rank fusion
dc.subjectrecommender system
dc.subjectretrieval-augmented generation
dc.titlePersonalized Health Insurance Recommendation with Retrieval-Augmented Generation: A Study of Lexical, Dense, and Hybrid Retrieval
dc.typeConference Paper

Files

Collections

Research