Fraud Pattern and Chargeback Analysis
Analyze payment fraud, chargeback trends, risky segments, and prevention levers using transaction, dispute, and customer behavior data.
Prompt Template
You are a payments risk analyst. Analyze fraud and chargeback patterns and recommend prevention actions. **Business type:** [marketplace / ecommerce / SaaS / fintech / subscription / travel] **Time period:** [date range] **Transaction volume:** [orders, revenue, average order value] **Chargeback volume:** [count, amount, rate] **Fraud signals available:** [AVS/CVV result, device ID, IP country, billing/shipping mismatch, velocity, email age] **Customer/order fields:** [country, product, channel, payment method, customer age, coupon, shipping speed] **Known incidents:** [promo abuse, account takeover, card testing, friendly fraud, refund abuse] **Current controls:** [3DS, manual review, fraud tool, rules, order holds] **Risk tolerance:** [minimize losses / minimize false positives / balanced] Provide: 1. **Executive summary** of fraud rate, chargeback rate, financial impact, and trend direction. 2. **Segment analysis** by channel, geography, product, payment method, device, new vs returning customer, and order value band. 3. **Pattern hypotheses** with evidence and confidence level. 4. **Rule candidates**: suggested prevention rules with estimated impact and false-positive risk. 5. **Manual review queue design**: priority score, required evidence, SLA, and decision outcomes. 6. **Dashboard spec** with leading indicators, lagging indicators, and alert thresholds. 7. **Experiment plan** to test new controls without harming legitimate conversion. 8. **Next data to collect** to improve detection quality. Use tables where helpful and separate confirmed findings from hypotheses.
Example Output
Fraud and Chargeback Readout: DTC Electronics
Executive Summary
Chargeback rate rose from 0.42% to 0.91% in four weeks, creating $48,200 in disputed revenue. The spike is concentrated in paid social orders for high-value accessories with expedited shipping.
Segment Findings
| Segment | Order Share | Chargeback Rate | Loss | Signal |
|---|---:|---:|---:|---|
| Paid social + new customers | 18% | 2.4% | $31,600 | High velocity, coupon stacking |
| AOV over $300 | 9% | 3.1% | $22,100 | Billing/shipping mismatch |
| Returning customers | 44% | 0.18% | $3,900 | Low risk |
Rule Candidates
| Rule | Expected Impact | False Positive Risk | Recommendation |
|---|---|---|---|
| Step-up 3DS for new customers with AOV > $250 and mismatch | High | Medium | Test on 50% traffic |
| Hold expedited orders with 3+ failed payment attempts | Medium | Low | Implement immediately |
| Block all paid social orders from high-risk countries | High | High | Do not implement; too blunt |
Dashboard Alerts
Alert when hourly card declines exceed 2x baseline, chargeback rate exceeds 0.75% for 7 days, or one device ID places more than 5 orders in 30 minutes.
Tips for Best Results
- 💡Separate fraud prevention from conversion protection; an overly aggressive rule can cost more than the fraud it stops.
- 💡Analyze chargebacks by order date and dispute date — they answer different questions.
- 💡Look for combinations of weak signals. One mismatch may be normal; mismatch plus velocity plus expedited shipping is a story.
- 💡Always estimate false positives before recommending blocks.
Related Prompts
Dataset Summary and Insights
Paste or describe a dataset and get an instant summary of key statistics, patterns, anomalies, and actionable insights.
SQL Query Writer for Business Reports
Generate SQL queries for common business reporting needs — revenue trends, cohort analysis, funnel metrics, and more.
Dashboard KPI Definition Framework
Define the right KPIs for your business dashboard with clear formulas, targets, and data sources.