Support Contact Reason Pareto Analysis Builder
Analyze customer support contact reasons with Pareto tables, volume trends, cost impact, CSAT signals, and root-cause reduction opportunities.
Prompt Template
You are a support analytics lead. Analyze support contact reasons for [company/product] and identify the highest-impact reduction opportunities. Data context: - Time period: [date range] - Dataset fields available: [ticket ID, created date, channel, contact reason, tags, product area, plan, segment, region, resolution time, CSAT, reopen, agent] - Contact reason taxonomy: [current categories, messy tags, free text, unknown] - Ticket volume: [number of tickets/chats/calls] - Business context: [recent launch, outage, policy change, pricing change, migration, seasonality] - Segments to compare: [new users, enterprise, free plan, geography, device, product line] - Cost assumptions: [cost per contact, handle time, escalation cost, agent capacity] - Quality concerns: [miscategorized tags, duplicates, bot contacts, spam, missing values] - Goal: [reduce tickets, improve self-service, fix product issue, staffing plan, executive report] Deliver: 1. Data cleaning and taxonomy normalization plan. 2. Pareto table showing contact reason volume, percent of total, cumulative percent, trend, handle time, CSAT, and cost impact. 3. Top 5 contact drivers with likely root causes and evidence needed. 4. Segment comparison to reveal where each issue is concentrated. 5. Opportunity sizing for product fixes, help content, automation, policy changes, or proactive messaging. 6. Dashboard layout with filters, charts, and alert thresholds. 7. Experiment backlog ranked by effort, impact, confidence, and owner. 8. Executive summary suitable for a support/product leadership review.
Example Output
Pareto Summary
The top 4 contact reasons drive 63% of all tickets. Password reset alone represents 21% of volume, but billing confusion has the highest cost because it takes 2.4x longer to resolve and has lower CSAT.
| Reason | Volume | % Total | Cum. % | Avg Handle Time | CSAT | Est. Monthly Cost |
|---|---:|---:|---:|---:|---:|---:|
| Password reset | 1,240 | 21% | 21% | 4.2m | 4.4 | €5,208 |
| Billing confusion | 910 | 15% | 36% | 11.1m | 3.6 | €9,435 |
Recommended Experiment
Rewrite the billing plan-change screen and send a proactive confirmation email. Measure billing-confusion contacts per 1,000 active accounts for 30 days.
Tips for Best Results
- 💡Include handle time and CSAT; ticket volume alone can hide expensive issues.
- 💡Normalize messy tags before drawing conclusions from a Pareto chart.
- 💡Compare by segment so one large customer group does not mask another group's pain.
- 💡Tie each recommendation to an owner: product, support ops, content, policy, or engineering.
Related Prompts
Data Quality Incident Root Cause Analysis Builder
Investigate metric discrepancies, broken pipelines, missing events, or dashboard errors with a structured data quality incident RCA and prevention plan.
Refund Rate Root Cause Analysis Builder
Analyze refund spikes by product, channel, cohort, reason code, and customer segment to identify root causes and revenue-saving actions.
Dataset Summary and Insights
Paste or describe a dataset and get an instant summary of key statistics, patterns, anomalies, and actionable insights.