One of the essential industries in most countries nowadays is telecommunication. The competition level in this industry has risen due to technological advancement and the growing number of operators. Depending on different strategies, companies work hard to succeed in this dynamic environment. There are three main strategies that are commonly used among companies to generate revenues and thrive in this industry [1]: (1) acquire new customers, (2) upsell the existing customers, and (3) increase the retention period of customers. However, considering the return of investment (RoI) from all of these strategies, the third strategy is the most profitable one [1]. It shows that retaining an existing customer costs much lower than acquiring a new one and also considered much easier to apply than the upselling strategy [2]. To implement the third strategy, companies have to decrease the potential of the customer movement from one provider to another, or known as "customer's churn rate".
Therefore, predicting customers who are likely to leave the company could theoretically represent a significant additional revenue.
Resources:
- Wei, C.-P., & Chiu, I.-T. (2002). Turning telecommunications call details to churn prediction: a data mining approach. Expert Systems with Application, 23(2), 103-112.
- Ascarza, E., Iyengar, R., & Schleicher, M. (2016). The Perils of Proactive Churn Prevention Using Plan Recommendations: Evidence from a Field Experiment. Journal of Marketing Research, 53(1), 46-60.
Supervised, Classification
Logistic Regression, Random Forest Classifier, XGBoost Classifier, LGBM Classifier, Simple Neural Network
F1 Score, Accuracy