Customer Churn Prediction Based on Multiple Linear Regression and Random Forest

Businesses are seeking to retain existing customers and reduce the cost of acquiring new customers. Therefore, customer churn rate prediction becomes an effective way to solve this problem. This study uses a dataset on telco customer churn to explore the application of multiple linear regression and random forest models in predicting customer churn. By analyzing various customer attributes, including service types, account details, and monthly fees, this paper aims to identify key factors contributing to churn. The random forest model outperformed multiple linear regression in terms of accuracy and stability, achieving an accuracy rate of 79.18% on the test set. However, the R^2 of the multiple linear regression is 0.275. The goodness of fit of the data set is low, but most of the 19 variables are statistically significant. Therefore, this study can further improve the prediction accuracy by changing the data set or combining hybrid models and deep learning technology. Our findings suggest that customer satisfaction, service usage, and total charges are significant factors in predicting customer churn. This paper can provide companies with valuable insights to improve customer retention, enhance customer experience, optimize customer relationships, reduce marketing costs, etc.