Given historical data on loans given out with information on whether or not the borrower defaulted (charge-off), can we build a model thatcan predict wether or nor a borrower will pay back their loan? This way in the future when we get a new potential customer we can assess whether or not they are likely to pay back the loan. Keep in mind classification metrics when evaluating the performance of your model!
- Data Cleaning and preprocessing.
- Feature Engineering.
- Data Visualization and Exploratory Data Analysis.
- Data Normalization and Scaling.
- Training using Sequential Model with Dense Layers having "relu" activation and final Dense output layer as "Sigmoid" as its a Binary class Classification task.
- Compiled using AdamOptmizer as optmizer and binary_crossentropy as the loss function.
- Solving Overfitting issues using EarlyStoppings Callbacks and Dropout Layers in Network.
- Hyperparameter Tuning the Algorithms yielding best results.
- Testing the model on custom reallife data.
https://www.kaggle.com/wordsforthewise/lending-club
- TensorFlow 2
- Keras
- Scikit-Learn
- Seaborn
- Matplotlib
- Pandas
- Numpy