In the rapidly evolving telecommunications sector, maintaining profitability and growth depends on customer retention. With the goal of identifying the critical elements influencing customer attrition and creating a useful predictive model, this study offers a thorough investigation of customer churn prediction using a telecom dataset. This study uses a dataset that contains a variety of client features, such as account details, demographic data, and service consumption trends. Here, the data preparation techniques are used to manage anomalies, missing values, and data normalisation. The study uses a range of machine learning methods to forecast churn, such as support vector machines, random forests, decision trees, logistic regression, and gradient boosting. Metrics including accuracy, then precision, also the recall, then F1 score, and also the area under the curve of receiver operating characteristic are used to assess each model’s performance (AUC-ROC). By use of cross-validation and hyperparameter adjustment, we guarantee the models’ resilience and generalizability. Significant churn predictors, including contract type, duration, monthly costs, and customer support interactions, are identified by our investigation. According to the research, month-to-month contract holders who have higher monthly fees and frequent contact with customer service are more likely to experience customer attrition. The model with the highest degree of prediction accuracy is the random forest, which has an AUC-ROC of 0.85, making it the best-performing model. This paper offers a useful foundation for putting churn prediction models into practice in addition to highlighting the important variables causing customer churn in the telecom industry. Telecom firms may lower churn rates by creating focused retention tactics, such personalised offers and better customer care, by proactively identifying at-risk clients. The findings highlight how crucial it is to use machine learning and data analytics to improve client retention and enable commercial success in the telecom sector.
Enhancing Telecom Customer Loyalty Through Churn Prediction Models
06.11.2024
593478 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Advancing Telecom Customer Churn using Deep Learning
IEEE | 2024
|Customer Churn Prediction using Machine Learning
IEEE | 2022
|Elsevier | 2024
|