ThabangTheActuaryCoder/retail-customer-churn-model

Retail Customer Churn Model

A GradientBoostingClassifier pipeline for predicting customer churn, trained on South African retail data.

Intended Use

This model is intended for educational and demonstration purposes as part of an end-to-end ML pipeline showcasing Databricks, MLflow, Azure ML, and Hugging Face Hub integration.

Model Details

Property	Value
Classifier	GradientBoostingClassifier
Pipeline steps	preprocessor -> classifier
Training samples	9,600
Test samples	2,400
Target column	target
Created	2026-06-16T15:37:49.920979+00:00

Evaluation Metrics

Metric	Score
Accuracy	0.8421
Precision	0.7084
Recall	0.5928
F1	0.6455
ROC AUC	0.8817

Confusion Matrix

ROC Curve

Feature Importance

Features

Numeric: monthly_spend_zar, days_since_last_purchase, num_support_tickets, loyalty_points, account_age_months, num_returns_last_year, avg_order_value_zar, num_orders_last_6m, discount_usage_rate

Categorical: membership_tier, preferred_channel, province

Sample Usage

import joblib
from huggingface_hub import hf_hub_download
import pandas as pd

# Download and load the model
model_path = hf_hub_download(
    repo_id="ThabangTheActuaryCoder/retail-customer-churn-model",
    filename="customer_churn_model.joblib",
)
model = joblib.load(model_path)

# Create a sample input
sample = pd.DataFrame([{"monthly_spend_zar": 0, "days_since_last_purchase": 0, "num_support_tickets": 0, "loyalty_points": 0, "account_age_months": 0, "num_returns_last_year": 0, "avg_order_value_zar": 0, "num_orders_last_6m": 0, "discount_usage_rate": 0, "membership_tier": 0, "preferred_channel": 0, "province": 0}])

# Predict
prediction = model.predict(sample)
probabilities = model.predict_proba(sample)
print(f"Prediction: {prediction}, Probabilities: {probabilities}")