Customer_churn_prediction

• Aim of this project is to implement machine learning model to predict customer churn of telecom company.

• Out of 29 features present in dataset, after normalizing and cleaning data, I've selected 11 features using RandomForestClassifier with ensemble learning.

• Used 80/20 training and testing data for model development.

• Logistic regression prediction gave me around 80% accuracy for customer churn prediction and that has still scope for better prediction after optimization.

• As a part of customer retention program, this model can help management to make correct decisions on their future plans.