-
Goal 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 15 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.
- Install Jupyter Notebook and Python 3
- Install Python libraries mentioned in requirements.txt for this project
- Open notebook (.ipynb) from this project with Jupyter Notebook