Take the quiz to get a recommendation from a logistic-regression model trained on our dataset.
⭐ Model accuracy is based on the uploaded data.csv and reflects how well this educational model predicts the held-out test data. Accuracy and feature importance should not be considered absolute facts about real-world lending.
This project uses a machine-learning model to estimate whether a person is likely to be approved for a $1,000 loan based on age, monthly income, employment status, credit history, and collateral.
We collected an initial set of information and used AI to expand the dataset to more than 200 records. The final cleaned dataset contains 215 records. Personal identifying information was not included.
Data privacy: The dataset does not contain names, addresses, or other identifying information.
Bias: A model can learn patterns and biases from its training data. This educational prediction should not be treated as a real bank lending decision.
Radman Abedi, Oliver James Thompson, Vojtech Kratochvil!