My Jupyter notebooks files where I used Tensorflow, SciKit Learn, NumPy, Pandas, Matplotlib, and Seaborn to build a model and evaluate its performance. LendingClub dataset is provided by Kaggle, and project is provided by Jose Portilla.
For this LendingClub data set, I did some exploratory data analysis on the correlation between the continuous feature variables and create new features, such as the 'loan_repaid' and 'zip_code'. I've also removed some unimportant data and filled out the remaining missing data. Then, I trained a sequential model to predict whether or not a customer will pay back the loan.