An evaluation of predictive customer segmentation for a German grocery retailer

• Autor(a) principal: Bohrer, Adrian
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/142644
• topic: Machine learning; Germany; Customer lifetime value; Predictive customer segmentation; E-grocery; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

This work project reports about an applied project in partnership with a German grocer that wanted to substitute its RFM model with a predictive customer lifetime segmentation model. A dataset for model development and evaluation was made available. The overarching question: "Can a predictive customer life time value segmentation model have better performance than the existing Recency, Frequency, and Monetary Value segmentation model? "will be answered by using a segmentation model evaluation framework. Finally, this master thesis’ findings show that a predictive customer lifetime value model has superior qualities to an RFM model but lacks reliability and cannot fully replace the old model.