vikas-sachan870/Loan-Default-Risk-Prediction-System ? reverse-engineered prompt
Reverse engineered prompt
Build me a clean Jupyter notebook for a loan default risk prediction project using the dataset in this repo. I want it to load the Excel file, clean the data, handle missing values and outliers, encode categorical columns, and scale the numeric ones where needed. Please include a short exploratory analysis with a few simple charts, like loan status distribution, income versus default rate, and a correlation heatmap.
Then train two models, a logistic regression baseline and a random forest model, split the data into training and test sets, and compare them using accuracy, precision, recall, F1 score, and ROC AUC. Show the results clearly and explain which model performs better in a simple way. If useful, add comments in the notebook so it is easy to follow, and make sure the whole thing runs end to end without missing steps.
Are you gonna build this?
make sure you review the code using coderabbit