Project Details: Deposit Term Subscription Prediction

This project is part of the Machine Learning Zoomcamp training held by DataTalksClub. In this Midterm Project, everything that has been learned in the previous weeks was applied in this project. The problem raised in this project is the prediction of whether potential bank clients will subscribe to the term deposit or not ('yes' or 'no' condition). What I do in this project:

1. Data preparation
2. Exploratory data analysis (EDA)
3. Split dataset → Train/Val/Test (60%/20%/20%)
4. Features importances
5. Choose model
6. Train the best and final model
7. Deploy final model to web services locally and cloud using Flask, pipenv, dockerfile, Heroku
8. Test the subscription prediction web services using potential client data