The factors of the bank customer (dis)loyalty in portfolio choices

摘要

The aim of this study is to find statistical methods able to support and to help banks to identify their customers' characteristics that might influence their (dis)loyalry in portfolio choices. In the first step, cluster analysis is used to identify the main customer's features. In the second step, in order to pinpoint these factors, survival analysis and logit regression are used jointly, based on the dataset of "Banca Popolare di Puglia e Basilicata". Survival analysis aims to estimate, in terms of time, the desire of customers to benefit from banking services in portfolio choices. Finally, logit regression aims to describe the potential unfaithful customer.