This project is a deployment of a machine learning model, or more precisely, a full pipeline that was developed to predict customer churn.
The model takes several inputs (such as credit score, age, balance, and other financial indicators) and determines whether a customer is likely to churn or not.
Within this pipeline, a Random Forest classifier was used to build the prediction model, leveraging its capability to handle complex relationships between features effectively.
The project covers the following:
- Data Preprocessing: Handling missing values, feature engineering, and scaling.
- Model Training and Evaluation: Building the Random Forest model and validating its performance.
- Deployment: Making the model accessible for real-time predictions through a deployed service.
This pipeline ensures efficient prediction and can be easily integrated into banking or financial applications to identify customers at risk of churn proactively.