-
Churn is a one of the biggest problem in the telecom industry.
-
For Telco companies it is key to attract new customers and at the same time avoid contract terminations to grow their revenue-generating base. Looking at churn, different reasons trigger customers to terminate their contracts, for example, better price offers more interesting packages, bad service experiences, or changes in customers’ personal situations.
-
Telcos apply machine learning models to predict churn on an individual customer basis and take countermeasures such as discounts, special offers, or other gratifications to keep their customers. A customer churn analysis is a typical classification problem within the domain of supervised learning.
-
Churn analytics provides valuable capabilities to predict customer churn and also define the underlying reasons that drive it. The churn metric is mostly shown as the percentage of customers that cancel a product or service within a given period (mostly months).
-
I have explored the following classficiation techniques and compared their accuracy and other metrics such as:
- ROC-AUC score
- True Positive Rate and False Positive Rate