Feature importance analysis for customer management of insurance products

Sohail, Misbah, Peres, Pedro and Li, Yuhua ORCID: https://orcid.org/0000-0003-2913-4478 2021. Feature importance analysis for customer management of insurance products. Presented at: 2021 International Joint Conference on Neural Networks (IJCNN), Virtual / Shenzhen, China, 18-22 July 2021. Proceedings of the International Joint Conference on Neural Networks. IEEE, pp. 1-8. 10.1109/IJCNN52387.2021.9533893

Preview

PDF - Accepted Post-Print Version Download (528kB) | Preview

Abstract

Optimizing customer contact strategies is important to improving customer experience, increasing sales and improving business profitability. This study focuses on finding an optimal time to contact customers, using demographic features provided by a private insurance broker and area characteristics from national census data. We train machine learning models and interpret the results using SHAP to analyze how each feature explains customer contactability. Among all the interesting results, we find that for older people, the best time to contact is during late evenings and nights.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	978-1-6654-4597-9
ISSN:	2161-4393
Date of First Compliant Deposit:	26 April 2021
Date of Acceptance:	10 April 2021
Last Modified:	30 Jul 2025 14:29
URI:	https://orca.cardiff.ac.uk/id/eprint/140765

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item