In the financial sector, insurance companies generate large volumes of data, including policy transactions, customer interactions, and risk assessments. These historical data on established customers provide opportunities to enhance decision-making processes and offer more customized services. However, data on potential new customers are often limited, due to a lack of historical records and to legal constraints on personal data collection. Despite these limitations, accurately predicting whether a potential new customer will generate benefits (high-performance) or incur losses (low-performance) is crucial for many service companies. This study used a real-world dataset of existing car insurance customers and introduced advanced machine learning models, to predict the performance of potential new customers for whom available data are limited. We developed and evaluated approaches based on traditional binary classification models and on more advanced boosting classification models. Our computational experiments show that accurately predicting the performance of potential new customers can significantly reduce operation costs and improve the customization of services for insurance companies.
机构:
Inst Med Res & Occupat Hlth, Zagreb 10000, CroatiaInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Fucic, Aleksandra
Galea, Karen S.
论文数: 0引用数: 0
h-index: 0
机构:
IOM, CHES, Edinburgh EH14 4AP, Midlothian, ScotlandInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Galea, Karen S.
Duca, Radu Corneliu
论文数: 0引用数: 0
h-index: 0
机构:
Univ Leuven, Ctr Environm & Hlth, B-3000 Leuven, BelgiumInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Duca, Radu Corneliu
El Yamani, Mounia
论文数: 0引用数: 0
h-index: 0
机构:
French Natl Publ Hlth Agcy, Sante Publ France, F-94415 St Maurice, FranceInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
El Yamani, Mounia
Frery, Nadine
论文数: 0引用数: 0
h-index: 0
机构:
French Natl Publ Hlth Agcy, Sante Publ France, F-94415 St Maurice, FranceInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Frery, Nadine
Godderis, Lode
论文数: 0引用数: 0
h-index: 0
机构:
Univ Leuven, Ctr Environm & Hlth, B-3000 Leuven, Belgium
IDEWE, Knowledge Informat & Res Ctr, B-3001 Heverlee, BelgiumInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Godderis, Lode
Halldorsson, Thorhallur Ingi
论文数: 0引用数: 0
h-index: 0
机构:
Natl Univ Hosp Iceland, Unit Nutr Res, IS-101 Reykjavik, Iceland
Univ Iceland, Sch Hlth Sci, Fac Food Sci & Nutr, IS-101 Reykjavik, IcelandInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Halldorsson, Thorhallur Ingi
Iavicoli, Ivo
论文数: 0引用数: 0
h-index: 0
机构:
Univ Naples Federico II, Dept Publ Hlth, I-80131 Naples, ItalyInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Iavicoli, Ivo
Ndaw, Sophie
论文数: 0引用数: 0
h-index: 0
机构:
Inst Natl Rech & Secur, F-54500 Vandoeuvre Les Nancy, Vandoeuvre Les, FranceInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Ndaw, Sophie
Ribeiro, Edna
论文数: 0引用数: 0
h-index: 0
机构:
Inst Politecn Lisboa, H&TRC Hlth & Technol Res Ctr, ESTeSL Escola Super Tecnol Saude, P-1990096 Lisbon, Portugal
Univ Lisbon, Inst Super Agron, Landscape Environm Agr & Food, P-1349017 Lisbon, Portugal
Univ Nova Lisboa, Ctr Invest & Estudos Saude Publ, Escola Nacl Saude Publ, P-1600560 Lisbon, PortugalInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Ribeiro, Edna
Viegas, Susana
论文数: 0引用数: 0
h-index: 0
机构:
Inst Politecn Lisboa, H&TRC Hlth & Technol Res Ctr, ESTeSL Escola Super Tecnol Saude, P-1990096 Lisbon, Portugal
Univ Nova Lisboa, Ctr Invest & Estudos Saude Publ, Escola Nacl Saude Publ, P-1600560 Lisbon, PortugalInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Viegas, Susana
Moshammer, Hanns
论文数: 0引用数: 0
h-index: 0
机构:
Med Univ Vienna, Ctr Publ Hlth, A-1090 Vienna, AustriaInst Med Res & Occupat Hlth, Zagreb 10000, Croatia
Moshammer, Hanns
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH,
2018,
15
(06):