telecom-churn-xgboost
Modelo de classificação binária para previsão de churn em clientes de telecomunicações.
Métricas (conjunto de teste — holdout 15%)
| Métrica | Valor |
|---|---|
| Recall(churn) | 0.7429 |
| F1 (weighted) | 0.7681 |
| ROC-AUC | 0.8162 |
| Accuracy | 0.7573 |
Uso
import joblib, pandas as pd
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(repo_id="RafaelPrime/telecom-churn-xgboost", filename="xgboost.joblib")
prep_path = hf_hub_download(repo_id="RafaelPrime/telecom-churn-xgboost", filename="preprocessor.joblib")
model = joblib.load(model_path)
preprocessor = joblib.load(prep_path)
# X_raw: DataFrame com as colunas originais do dataset
X_proc = preprocessor.transform(X_raw)
pred = model.predict(X_proc)
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support