Tabular Classification
Scikit-learn
Joblib
logistic-regression
credit-risk
loan-default
tabular
binary-classification
Instructions to use gusdelact/loan-default-logreg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use gusdelact/loan-default-logreg with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("gusdelact/loan-default-logreg", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_name": "loan-default-logreg", | |
| "model_type": "LogisticRegression", | |
| "task": "binary_classification", | |
| "target": "loan_default", | |
| "target_classes": [ | |
| "no_default", | |
| "default" | |
| ], | |
| "positive_class": "default", | |
| "trained_at": "2026-06-24T13:50:48.902678", | |
| "python_version": "3.11.15", | |
| "library_versions": { | |
| "scikit-learn": "1.9.0", | |
| "numpy": "2.4.6", | |
| "scipy": "1.17.1", | |
| "pandas": "3.0.3", | |
| "joblib": "1.5.3" | |
| }, | |
| "decision_threshold": 0.8155, | |
| "threshold_rationale": "minimiza costo esperado 3:1 (3*FP+1*FN) sujeto a precision>=0.70 y recall>=0.40 (ver notes/04_design_validation.md)", | |
| "feature_order": [ | |
| "age", | |
| "income", | |
| "credit_score", | |
| "dependents", | |
| "home_owner" | |
| ], | |
| "raw_feature_order": [ | |
| "age", | |
| "income", | |
| "credit_score", | |
| "dependents", | |
| "home_owner" | |
| ], | |
| "processed_feature_order": [ | |
| "age", | |
| "credit_score", | |
| "dependents", | |
| "income", | |
| "home_owner" | |
| ], | |
| "raw_feature_meta": { | |
| "age": { | |
| "type": "int", | |
| "min": 20, | |
| "max": 69, | |
| "default": 44, | |
| "label": "Edad (anios)" | |
| }, | |
| "income": { | |
| "type": "float", | |
| "min": 4000, | |
| "max": 100000, | |
| "default": 20000, | |
| "label": "Ingreso anual" | |
| }, | |
| "credit_score": { | |
| "type": "int", | |
| "min": 300, | |
| "max": 849, | |
| "default": 580, | |
| "label": "Credit score (FICO)" | |
| }, | |
| "dependents": { | |
| "type": "int", | |
| "min": 0, | |
| "max": 4, | |
| "default": 2, | |
| "label": "Numero de dependientes" | |
| }, | |
| "home_owner": { | |
| "type": "binary", | |
| "min": 0, | |
| "max": 1, | |
| "default": 0, | |
| "label": "Propietario de vivienda (0=no, 1=si)" | |
| } | |
| }, | |
| "metrics_at_operating_point": { | |
| "precision_default": 0.9677, | |
| "recall_default": 0.7692, | |
| "f1_default": 0.8571, | |
| "expected_cost_3to1": 12, | |
| "pr_auc": 0.9381, | |
| "roc_auc": 0.9804 | |
| }, | |
| "preprocessor_file": "preprocessor.joblib", | |
| "model_file": "model.joblib" | |
| } |