Total Deposit Customers
45,211
▲ 3.2% vs last quarter
Deposits Under Management
₹892 Cr
▲ 5.1% vs last quarter
High-Risk Customers
1,847
▲ 12.4% vs last month
Predicted Deposit Outflow
₹38.4 Cr
⚠ Next 90 days
Retention Opportunities
3,124
▲ High-value pipeline
Deposit Retention Rate
87.3%
▲ 4.1% vs prior year
Customer Risk Intelligence Table
Kaggle UCI Banking Dataset · 45,211 customers · Click row for 360° view
| Customer Name | Deposit Balance | Deposit Type | Risk Score | Outflow Prob. | Value At Risk | Action |
|---|
AI Retention Copilot
Real-time alerts · Last updated 2h ago
Deposit Outflow Prediction Center
AI-predicted deposit movements in next 30–90 days
| Customer | Risk Type | Probability | Expected Outflow | Timeframe | Suggested Intervention | Priority |
|---|
AI Risk Explanation Engine
Top contributing factors · Rahul Sharma (Risk Score: 92)
Overall Risk Score
92 / 100
Next Best Action Center
AI recommendations with confidence scores
Portfolio Protection Center
Year-to-date deposit protection performance
Deposits Protected
₹12.4 Cr
via AI-driven retention
Outflow Prevented
₹8.7 Cr
outflow intercepted YTD
Campaign Success Rate
74.2%
retention campaigns effective
High-Value Customers Saved
842
customers retained YTD
Revenue Preserved
₹3.1 Cr
interest income preserved
📋 Today's Deposit Protection Queue
Top 10 customers requiring immediate retention action · Ranked by deposit value × risk score
Analytics & Predictive Intelligence
AI-powered deposit risk and retention analytics
Deposit Risk Distribution
Critical 8%
High 18%
Medium 32%
Low 42%
Deposit Outflow Prediction Trend
Customer Retention Funnel
Deposit Portfolio Breakdown
Retention Opportunity Pipeline · Monthly Forecast
AI Intelligence Features
Powered by machine learning on Kaggle UCI Banking Dataset
Deposit Attrition Prediction
ML model predicts deposit withdrawal probability using 17 behavioral and transactional features from the UCI bank marketing dataset.
Model Accuracy: 91.4% · AUC-ROC: 0.94
FD Breakage Prediction
Detects fixed deposit breakage risk 45 days in advance using maturity patterns, balance trends, and economic signals.
F1 Score: 0.89 · Precision: 87.2%
Customer Churn Detection
Binary classification model trained on 45,211 records. Identifies churn signals including balance reduction, contact frequency, and digital inactivity.
Recall: 88.6% · Specificity: 93.1%
Retention Recommendation Engine
Collaborative filtering engine recommends optimal retention offers based on customer segment, deposit value, risk score, and historical campaign data.
Click-through Rate: 34% · Conversion: 22%
Portfolio Protection Monitoring
Real-time monitoring of deposit portfolio health with automated alerts when portfolio risk threshold exceeds defined limits.
Alert Latency: <2h · Coverage: 100%
Next Best Action AI
Reinforcement learning model selects the most effective retention action for each customer based on predicted response rates and deposit value.
Action Effectiveness: 74% · ROI: 4.2x
Business Impact · AI vs Traditional
Measured outcomes from platform deployment across retail banking portfolio
❌ Without AI (Traditional Approach)
Reactive retention — action after customer leaves
ReactiveAverage deposit loss per customer: ₹2.8L/quarter
High LossRisk detection time: 14–21 days after first signal
Late SignalRetention campaign conversion rate: 12–15%
Low ROI✅ With AI (DRI Platform)
Predictive retention — 45 days early warning
Proactive40% higher deposit retention vs prior year
+40%Risk detection: 75% faster with 2-hour alert latency
Fast₹12 Crore deposits protected · 65% campaign improvement
₹12 Cr75%
Faster Risk Detection
40%
Higher Deposit Retention
₹12Cr
Deposits Protected
65%
Better Campaign Results