DATASET PROFILE REPORT

Generated: 2025-12-02
File: /tmp/sample_customers.csv

═══════════════════════════════════════════════════════════

OVERVIEW

═══════════════════════════════════════════════════════════
• Total Rows: 10 customers
• Total Columns: 8
• File Size: ~1 KB
• Overall Completeness: 96.2% (3 missing values)

═══════════════════════════════════════════════════════════

DATA STRUCTURE

═══════════════════════════════════════════════════════════

Column Types:

• Numeric: 2 columns

• age, revenue

• Text/Categorical: 5 columns

• customer_id, name, email, region, customer_type

• Date: 1 column

• signup_date

═══════════════════════════════════════════════════════════

NUMERIC COLUMNS - KEY STATISTICS

═══════════════════════════════════════════════════════════

AGE

Range:        28 to 52 years
Mean:         36.7 years
Median:       35.0 years
Std Dev:      7.5 years
Distribution: Moderately right-skewed (most customers under 40)

✓ No outliers detected
✓ All values present (no missing data)

REVENUE

Range:        $0.00 - $15,600.00
Mean:         $3,440.20
Median:       $1,175.25
Std Dev:      $4,990.69
Distribution: Highly right-skewed (most customers under $2,000)

⚠ Outliers Detected: 2 values identified as statistical outliers

• Alice Brown (C004): $15,600.00 - High-value Enterprise customer
• Frank Miller (C008): $8,900.50 - High-value Enterprise customer

⚠ Zero Revenue: 1 customer with $0.00 revenue

• Henry Ford (C010): New customer, signed up 2023-03-20, no purchases yet

═══════════════════════════════════════════════════════════

CATEGORICAL COLUMNS - KEY INSIGHTS

═══════════════════════════════════════════════════════════

CUSTOMER_TYPE

• SMB: 6 customers (60%)
• Enterprise: 4 customers (40%)

REGION

Customers are evenly distributed across four regions:

• North: 3 customers (30%)
• South: 3 customers (30%)
• East: 2 customers (20%)
• West: 2 customers (20%)

EMAIL

✓ 7 valid email addresses
⚠ 3 missing emails (30%) - Impacts marketing capabilities

═══════════════════════════════════════════════════════════

DATE ANALYSIS

═══════════════════════════════════════════════════════════

SIGNUP_DATE

Date Range:   November 5, 2022 - April 2, 2023
Time Span:    148 days (~5 months)

Most recent signups occurred in early 2023, with steady customer acquisition over the period.

═══════════════════════════════════════════════════════════

CORRELATION INSIGHTS

═══════════════════════════════════════════════════════════

Strong Positive Correlation:

✓ age ↔ revenue: r=0.76 (strong positive)
→ Older customers generate significantly higher revenue
→ This could indicate:
- More established financial capacity
- Greater business needs (especially for Enterprise)
- Higher decision-making authority

This is a key finding for targeting and segmentation strategies.

═══════════════════════════════════════════════════════════

DATA QUALITY ISSUES

═══════════════════════════════════════════════════════════

Missing Values:

⚠ email: 3 missing (30% of dataset)

• Affected customers: C003 (Bob Wilson), C006 (Diana Prince), C010 (Henry Ford)
• Impact: Cannot send email marketing campaigns to 30% of customer base
• Pattern: No clear geographic or customer type pattern

Potential Data Issues:

⚠ Zero Revenue Customer:

• Henry Ford (C010): $0.00 revenue despite signup
• Most recent signup (March 20, 2023) - may be inactive or in trial period
• Action needed: Investigate customer status and engagement

Quality Checks Passed:

✓ No duplicate rows detected
✓ All customer IDs are unique
✓ All names are unique
✓ No inconsistent data formats
✓ Date formats are consistent

═══════════════════════════════════════════════════════════

KEY INSIGHTS

═══════════════════════════════════════════════════════════

1. ENTERPRISE CUSTOMERS DRIVE REVENUE

Critical Finding: Enterprise customers (40% of base) generate 10x higher revenue than SMB customers on average.

• Enterprise average: $7,510
• Enterprise median: $6,050
• SMB average: $727
• SMB median: $780

→ Implication: Focus acquisition and retention efforts on Enterprise segment for maximum revenue impact.

2. AGE = REVENUE PREDICTOR

Strong correlation (r=0.76) between customer age and revenue generation.

• Customers 40+ generate significantly higher revenue
• Younger customers (under 35) cluster in lower revenue ranges

→ Implication: Age could be a valuable targeting criterion for marketing campaigns and lead scoring.

3. REVENUE CONCENTRATION

Revenue is highly concentrated:

• Top 2 customers (20%) generate ~$24,500 (71% of total revenue)
• Bottom 6 customers (60%) generate only ~$4,400 (13% of total revenue)

→ Implication: High customer concentration risk - losing top customers would significantly impact revenue.

4. CUSTOMER LIFECYCLE STAGES

Dataset shows customers at different lifecycle stages:

• Active high-value: 2 Enterprise customers generating >$8K
• Moderate contributors: 6 SMB customers with steady revenue
• New/Inactive: 1 customer with zero revenue (potential churn risk)

═══════════════════════════════════════════════════════════

RECOMMENDATIONS

═══════════════════════════════════════════════════════════

IMMEDIATE ACTIONS (Week 1):

1. ✅ Collect Missing Email Addresses

   • Contact C003 (Bob Wilson), C006 (Diana Prince), C010 (Henry Ford)
   • Implement mandatory email collection at signup
   • Without emails, 30% of customers cannot receive communications

2. ✅ Investigate Zero-Revenue Customer

   • Follow up with Henry Ford (C010) - signed up but no purchases
   • Determine if customer is in trial, inactive, or needs support
   • Consider activation campaign or win-back strategy

3. ✅ Review High-Value Customers

   • Verify Alice Brown ($15,600) and Frank Miller ($8,900) transactions
   • If accurate, analyze what drove their high spend
   • Create case studies to replicate success

STRATEGIC RECOMMENDATIONS:

4. Segment All Future Analyses by Customer Type

   • Enterprise and SMB behave completely differently (10x revenue gap)
   • Build separate strategies, campaigns, and metrics for each segment
   • Consider different pricing, features, or support tiers

5. Age-Based Targeting for Acquisition

   • Strong age-revenue correlation (r=0.76) suggests targeting older prospects
   • Focus marketing on 40+ demographic for higher-value customers
   • Test age-based messaging and channel selection

6. Address Revenue Concentration Risk

   • Top 2 customers represent 71% of revenue - high risk
   • Implement customer success program for high-value accounts
   • Diversify customer base to reduce dependency

7. Customer Activation Program

   • Monitor new signups for revenue activity within 30 days
   • Create automated onboarding and activation campaigns
   • Identify and address barriers to first purchase

ANALYSIS RECOMMENDATIONS:

8. For Revenue Modeling: Use log transformation due to extreme right skew (skewness: 2.05)

9. For Forecasting: Consider Enterprise and SMB separately - different behavior patterns

10. For Segmentation: Include age as a key variable given strong predictive power

═══════════════════════════════════════════════════════════

VISUALIZATIONS

═══════════════════════════════════════════════════════════

Included visualizations show:

• Revenue distribution with median/mean markers (highly right-skewed)
• Revenue by customer type (Enterprise dominance visible)
• Age vs Revenue scatter plot (positive correlation visible)
• Correlation heatmap (strong age-revenue relationship)
• Missing data visualization (30% email gap highlighted)

All visualizations saved to /tmp/ directory.

═══════════════════════════════════════════════════════════

DATASET READINESS ASSESSMENT

═══════════════════════════════════════════════════════════

Current State: ✅ READY for analysis with caveats

Strengths:

• Clean data structure with no duplicates
• High completeness (96.2%)
• Clear segmentation variables (customer_type, region)
• Strong predictive relationships identified (age-revenue)
• Consistent date formatting

Limitations:

• Small sample size (n=10) - findings may not generalize
• 30% missing email addresses limits marketing capabilities
• High revenue skew requires careful statistical handling
• One inactive customer needs investigation

Best For:

• Customer segmentation exploration
• Revenue pattern analysis
• Hypothesis generation for larger datasets
• Proof-of-concept modeling

Not Suitable For:

• Statistical significance testing (sample too small)
• Predictive modeling without additional data
• Definitive business conclusions

═══════════════════════════════════════════════════════════

NEXT STEPS

═══════════════════════════════════════════════════════════

The dataset is small but clean and reveals important patterns.

Priority actions:

1. Fix email gaps (30% missing) before any email campaigns
2. Investigate zero-revenue customer (C010)
3. Analyze Enterprise vs SMB separately - they are fundamentally different segments

Analysis opportunities:

• Customer lifetime value modeling (if you have historical data)
• Churn risk analysis (need more behavioral data)
• Revenue forecasting by segment
• Age-based targeting strategies

To expand insights, consider adding:

• Transaction history (frequency, recency, product mix)
• Customer engagement metrics (logins, support tickets)
• Acquisition channel data
• Tenure/lifetime metrics

---

Summary: This small dataset (10 customers) provides a clear snapshot showing Enterprise customers driving most revenue, a strong age-revenue correlation, and critical data quality issues (30% missing emails, 1 zero-revenue customer). Focus on segment-specific strategies and fix data gaps before scaling analysis.