This paper is being realized as part of our last year in master’s degree in economics. It aims at studying a firm’s most valuable asset namely its customers. To that end, we adopt a quantitative approach based on econometrics and data analysis with a threefold purpose to :

  • model a customer portfolio as a set of customer segments;
  • predict and analyse customer churn;
  • estimate a customer portfolio’s overall value.

After having defined the subject’s key concepts, we apply duration models and machine learning techniques to a kaggle dataset related to customers of a fictional telecommunications service provider (TSP).

Keywords: customer portfolio management (CPM), churn, customer value, duration models, machine learning, telecom.