Predicts the likelihood of customers canceling their insurance policies, enabling proactive retention efforts.
1import pandas as pd
2from transformers import pipeline
3
4predictor = pipeline("tabular-classification", model="gcc-insurance-ml-models/customer-churn-predictor")
5
6customer = {
7 "tenure_months": 8,
8 "claims_count": 1,
9 "claim_denied": True,
10 "payment_issues": 0,
11 "premium_increase_pct": 12,
12 "app_logins_30d": 0,
13 "support_tickets": 2
14}
15
16result = predictor(customer)
17# Output: {'churn_probability': 0.67, 'segment': 'critical', 'top_factors': ['claim_denied', 'premium_increase']}
Churn Score > 60%
↓
[Identify Top Factors]
↓
claim_denied → Escalate review, offer goodwill
price_increase → Discount offer, bundle savings
payment_issues → Flexible payment plan
low_engagement → Personalized outreach
