Evaluating the Risk of Home Equity Line of Credit (HELOC) Applications

• Designed interface that sales representatives in a bank/credit card company can use to decide on accepting or rejecting applications
• Developed a predictive model to assess credit risk
• Trained and evaluated model performance

Data Profiles

• Our interface included integration and analytics.
• The interface allows new users to begin effective interaction and could easily achieve maximal performance.
• There are a total of 23 features in the dataset.
• We choose the Boosting Model to make predictions.

Insights

• A higher score indicates that the specific feature will have a larger effect on the model.
• the prediction results of whether the client’s application should be “Reject” or “Accept” are shown at the bottom of the interface’s input.