Data Analysis & Visualization

Turn data into actionable insights

🎯 Purpose

Analyze structured data to:

• Find patterns & trends
• Generate statistical insights
• Create visualizations
• Build reports
• Make data-driven recommendations

📊 Capabilities

Data Sources

• CSV files
• Excel spreadsheets
• JSON data
• Database queries
• API responses
• Web scraping

Analysis Types

1. Descriptive Analytics

   • Summary statistics
   • Distributions
   • Aggregations

2. Diagnostic Analytics

   • Root cause analysis
   • Correlation analysis
   • Trend analysis

3. Predictive Analytics

   • Forecasting
   • Pattern recognition
   • Trend projection

4. Prescriptive Analytics

   • Recommendations
   • Optimization suggestions
   • Action items

🛠️ Tools & Techniques

Statistical Analysis

- Mean, Median, Mode
- Standard Deviation
- Variance
- Percentiles
- Correlation coefficients
- Regression analysis

Data Visualization

- Line charts (trends over time)
- Bar charts (comparisons)
- Pie charts (proportions)
- Scatter plots (correlations)
- Heat maps (patterns)
- Histograms (distributions)

Pattern Recognition

- Seasonal patterns
- Growth trends
- Anomalies/outliers
- Clusters
- Segments

💬 Response Template

## 📊 Data Analysis Report

**Dataset:** [Description]
**Records:** [Count]
**Time Period:** [If applicable]

### Key Findings

1. **📈 [Finding 1]**
   - Detail: [Explanation]
   - Impact: [Why it matters]

2. **📉 [Finding 2]**
   - Detail: [Explanation]
   - Impact: [Why it matters]

3. **🎯 [Finding 3]**
   - Detail: [Explanation]
   - Impact: [Why it matters]

### Statistics

| Metric | Value | Change |
|--------|-------|--------|
| Total | X | +X% |
| Average | X | +X% |
| Median | X | +X% |
| Min/Max | X / Y | - |

### Visualizations

[Charts/graphs would be generated here]

### Patterns Identified

✅ **Positive:** [Good trends]
⚠️ **Concerns:** [Worrisome trends]
🔍 **Anomalies:** [Unusual data points]

### Recommendations

1. **[Action 1]** - [Reasoning]
2. **[Action 2]** - [Reasoning]
3. **[Action 3]** - [Reasoning]

### Next Steps

- [ ] Deep dive into [specific area]
- [ ] Investigate [anomaly]
- [ ] Implement [recommendation]
- [ ] Monitor [metric]

**Questions?**

📋 Usage Examples

Example 1: Sales Analysis

User: "Analyze Q1 2026 sales data"

AI:
## 📊 Data Analysis Report

**Dataset:** Q1 2026 Sales
**Records:** 1,247 transactions
**Time Period:** Jan 1 - Mar 31, 2026

### Key Findings

1. **📈 Revenue up 23% QoQ**
   - Detail: $1.2M → $1.48M
   - Impact: Exceeds target by 8%

2. **📉 Conversion rate dropped in March**
   - Detail: 3.2% → 2.8%
   - Impact: ~$50K potential loss

3. **🎯 Top product: Widget Pro**
   - Detail: 34% of revenue
   - Impact: Focus marketing here

### Recommendations

1. Investigate March conversion drop
2. Double down on Widget Pro marketing
3. Analyze customer segments for upsell

Example 2: User Behavior

User: "Find patterns in user activity data"

AI:
- Analyzes login patterns
- Identifies peak usage times
- Finds feature adoption rates
- Spots churn indicators
- Recommends engagement strategies

🎯 Success Metrics

✅ Insights are actionable
✅ Visualizations are clear
✅ Patterns are meaningful
✅ Recommendations are data-driven
✅ Analysis is accurate
✅ User can make decisions from this

---

Status: Active
Version: 1.0.0
Last Updated: 2026-04-10