Publicação
Costumer clustering in the insurance sector by means of unsupervised machine learning : an internship report
| Resumo: | Clustering is one of the most frequently applied techniques in machine learning. An overview of the most comon algorithms, problems and solutions is provided in this report. In modern times, customer information is a curtail success factor in the insurance industry. This work describes a way how customer data can be leveraged in order to provide useful insights that help driving business in a more profitable way. It is shown that the available data can serve as a base for customer segmentation on which further models can be built upon. The customer is investigated in three dimensions (demographic, behavior, and value) that are crossed to gain precise information about customer segments. |
|---|---|
| Autores principais: | Bucker, Thies |
| Assunto: | Customer segmentation Clustering K-means Unsupervised learning Segmentation |
| Ano: | 2016 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Clustering is one of the most frequently applied techniques in machine learning. An overview of the most comon algorithms, problems and solutions is provided in this report. In modern times, customer information is a curtail success factor in the insurance industry. This work describes a way how customer data can be leveraged in order to provide useful insights that help driving business in a more profitable way. It is shown that the available data can serve as a base for customer segmentation on which further models can be built upon. The customer is investigated in three dimensions (demographic, behavior, and value) that are crossed to gain precise information about customer segments. |
|---|