Churn Prediction — CDR Analytics

At-Risk Subscribers

—

Critical Risk

—

Avg Usage Decline

—

Churned Subscribers

—

CDR-Based Churn Prediction

Analyzes Call Detail Records (CDR) to predict subscriber churn by tracking usage decline patterns, reduced call/SMS/data activity, shrinking social networks, and decreasing geographic mobility across Philippine telecom networks.

Early identification of at-risk subscribers enables proactive retention campaigns, personalized offers, and targeted interventions — reducing churn rates by up to 15-25% in Philippine telecom markets.

Churn Analysis

Risk Distribution

Risk Level Distribution

Usage Change Distribution

Churn Analysis

Regional Analysis

Churn Rate by Region

Monthly Active Subscriber Trend

At-Risk Subscribers

Subscribers with significant usage decline indicating potential churn

MSISDN	Region	City	Recent Activity	Prior Activity	Usage Change %	Risk

How CDR Churn Detection Works

1CDR Collection — Aggregate call, SMS, and data session records across all network elements over rolling time windows

2Usage Profiling — Build behavioral baselines: call frequency, SMS volume, data consumption, contact diversity, and site mobility

3Decline Detection — Compare recent activity against prior baselines to identify significant usage drops and behavioral shifts

4Risk Scoring — Multi-factor churn risk score combining usage decline, social network shrinkage, and geographic pattern changes

5Retention Action — At-risk subscribers flagged for proactive retention: personalized offers, loyalty rewards, or customer outreach

AI Deep Analysis — Churn Prediction GPT-4.1

AI is analyzing churn patterns...

AI Analyst

Welcome to the Data Manager AI Analyst. I can help you with:

Revenue leakage analysis & recovery strategies
Fraud pattern detection insights
Compliance & AML risk assessment
Data quality recommendations
Executive-level briefings

Ask me anything about your banking data platform.