Endüstri Mühendisliği Seminerler Serisi / Birol Yüceoğlu

Title: Using Data Analytics for Customer Churn Prediction: A Case Study for an Online Retailer

Abstract: We present a new decision support system for predicting customer churn for a leading online fast moving consumer goods retailer. The proposed system is based on the recent data analytics and machine learning tools. The main steps of our development are the data cleaning, the feature extraction and the prediction with supervised learning methods. The prediction step requires a careful definition of a churning customer in the retail sector for it is not obvious to identify the agents in such a non-contractual setting. After discussing different scenarios for customer attrition, we conduct an empirical study by using the past data of the company. Our results and observations contribute to the existing literature along two dimensions. First, we present the proposed decision support system as a promising application of data analytics to predict churn in online retailing. Second, we answer two questions from the literature on the effect of the length of the customer event history and the staying power of the prediction models. We argue that our results for the retail industry here validate the findings obtained for other industries studied in the literature.

Bio: Birol Yüceoğlu studied industrial engineering at Sabancı University. After finishing his M.S. degree at the same university, he received his Ph.D. on Operations Research from Maastricht University, the Netherlands. Currently, he is working as an R&D projects evaluation team leader at Migros Turkey and teaching the Practical Case Studies in Data Analytics course in the Data Analytics program at Sabancı University. His research interests include data analytics, graph theory and integer programming.

Venue: AB1 - 511