In times where competition among banks has arguably risen to an all-time high, a better understanding of a bank’s customer base, and hence its most valuable customers, is paramount in order to ensure long-term survival. Notably, banks are in possession of an unparalleled richness of data, which has partly remained untapped as of today. Firstly, this work provides a brief overview of Customer Lifetime Value (CLV) applications with special attention for the retail banking industry. Furthermore, using data from a retail bank, this study aims to empirically test and evaluate competing modeling and prediction approaches, using regression and machine learning techniques alike, in both single-product and multi-product settings. Additionally, one of the goals of this study is to introduce new, sector-specific factors to CLV-modeling, which are vital to garner a profound understanding of customer behaviour in this context. Profit margins are, where applicable, customer-specific and determined in consultation with product-experts.
|Title of host publication||EURO 2016: 28th European Conference on Operational Research|
|Subtitle of host publication||The Association of European Operational Research Societies|
|Publication status||Published - Jul 2016|
|Event||EURO 2016: 28th European Conference on Operational Research - Poznan, Poland|
Duration: 3 Jul 2016 → 6 Jul 2016
|Abbreviated title||EURO 2016|
|Period||3/07/16 → 6/07/16|