Predicting Customer Behaviour With Classifiers

Customer Relationship Management (CRM) is a key element of modern marketing approaches. A 2017 poll found it to be the most popular field for the application of analytics, data science and machine learning.

This work addresses the challenges of the KDD Cup 2009, predicting the propensity of customers to switch provider (churn), buy new products or services (appetency), or buy upgrades or add-ons proposed to them to make the sale more profitable (up-selling). Comparing results against other competition entries, the gradient boosting classifier outperformed other tested models, placing it 34th of 89 overall.

Master’s Degree Intelligent Systems paper grade 88% | Viva presentation | Source code