A credit risk text classification pipeline designed to simulate real-world modeling workflows. This project uses financial text data to predict borrower risk, incorporating data cleaning, NLP preprocessing, and model evaluation—emphasizing skills in feature engineering, model pipeline structuring, and explainable machine learning.
data-science machine-learning random-forest exploratory-data-analysis pipelines classification logistic-regression confusion-matrix data-cleaning gradient-boosting precision-recall-curve roc-auc-curve model-evaluation-metrics test-train-split
-
Updated
May 4, 2025 - Python