Lead Scoring Model - Comprehensive Framework
Date: 2024
Version: 1.0
Category: Revenue Operations - Lead Management
Executive Summary
Model Overview
This predictive lead scoring model combines demographic, firmographic, behavioral, and engagement data to identify sales-ready leads with 85% accuracy. The model uses a 100-point scale with dynamic scoring that adapts based on conversion patterns.
Key Outcomes
- 45% increase in sales productivity by focusing on high-score leads
- 2.3x higher conversion rate for leads scoring 70+
- 38% reduction in sales cycle for properly scored leads
- 67% improvement in marketing-to-sales handoff quality
Scoring Framework
Point Scale & Categories
| Score Range | Category | Action | Conversion Rate | Priority |
|---|---|---|---|---|
| 80-100 | Hot Lead | Immediate sales contact | 42% | Critical |
| 60-79 | Warm Lead | Sales outreach within 24h | 24% | High |
| 40-59 | Qualified Lead | Nurture with targeted content | 12% | Medium |
| 20-39 | Early Stage | General nurture campaign | 5% | Low |
| 0-19 | Cold Lead | Newsletter only | 1% | Minimal |
Demographic Scoring (30 Points Max)
Job Title/Seniority (15 points)
| Title Category | Points | Examples |
|---|---|---|
| C-Level/Owner | 15 | CEO, CFO, CTO, CMO, Founder |
| VP/Director | 12 | VP Sales, Director of Operations |
| Senior Manager | 9 | Senior Sales Manager, Head of Marketing |
| Manager | 6 | Sales Manager, Marketing Manager |
| Individual Contributor | 3 | Sales Rep, Analyst |
| Other/Unknown | 0 | Consultant, Student, Blank |
Department/Function (10 points)
| Department | Points | Rationale |
|---|---|---|
| Sales | 10 | Direct buying authority |
| Revenue Operations | 10 | Process ownership |
| Marketing | 8 | Influence and budget |
| Executive | 8 | Decision maker |
| IT | 6 | Technical evaluator |
| Finance | 5 | Budget approval |
| Customer Success | 4 | Expansion opportunity |
| Other | 2 | Potential influencer |
Years of Experience (5 points)
| Experience | Points | Insight |
|---|---|---|
| 10+ years | 5 | Senior decision maker |
| 5-10 years | 4 | Established professional |
| 2-5 years | 3 | Growing influence |
| 0-2 years | 1 | Limited authority |
| Unknown | 0 | No data |
Firmographic Scoring (30 Points Max)
Company Size by Revenue (10 points)
| Annual Revenue | Points | Segment |
|---|---|---|
| $100M+ | 10 | Enterprise |
| $50M-$100M | 8 | Upper Mid-Market |
| $10M-$50M | 7 | Mid-Market |
| $5M-$10M | 5 | Lower Mid-Market |
| $1M-$5M | 4 | Small Business |
| <$1M | 2 | Startup |
| Unknown | 0 | No data |
Company Size by Employees (10 points)
| Employee Count | Points | Category |
|---|---|---|
| 1000+ | 10 | Enterprise |
| 500-999 | 8 | Large |
| 100-499 | 7 | Medium |
| 50-99 | 5 | Small-Medium |
| 10-49 | 3 | Small |
| 1-9 | 1 | Micro |
Industry Fit (10 points)
| Industry | Points | Win Rate |
|---|---|---|
| Technology/Software | 10 | 38% |
| Financial Services | 9 | 34% |
| Healthcare | 8 | 31% |
| Manufacturing | 7 | 28% |
| Retail/E-commerce | 6 | 24% |
| Professional Services | 5 | 22% |
| Education | 4 | 18% |
| Non-profit | 2 | 12% |
| Government | 2 | 8% |
| Other | 1 | 15% |
Behavioral Scoring (40 Points Max)
Website Engagement (15 points)
| Activity | Points | Frequency Multiplier |
|---|---|---|
| Pricing Page Visit | 5 | x1.5 if 3+ times |
| Demo Request Page | 4 | x1.5 if 2+ times |
| Case Study Download | 3 | x1.3 per additional |
| Product Pages (5+) | 3 | x1.2 if 10+ pages |
| Blog Reading (3+) | 2 | x1.1 if 5+ posts |
| About Us/Team | 2 | One time only |
| Careers Page | -2 | Job seeker indicator |
Content Engagement (10 points)
| Content Type | Points | Intent Signal |
|---|---|---|
| ROI Calculator Use | 5 | High purchase intent |
| Whitepaper Download | 3 | Research phase |
| Webinar Attendance | 3 | Active evaluation |
| Case Study Download | 3 | Solution validation |
| Template Download | 2 | Problem awareness |
| Newsletter Signup | 1 | Early interest |
Email Engagement (10 points)
| Action | Points | Recency Bonus |
|---|---|---|
| Reply to Sales Email | 5 | +2 if within 24h |
| Click Multiple Links | 3 | +1 if 3+ clicks |
| Open 5+ Emails | 2 | +1 if consistent |
| Forward Email | 3 | Sharing internally |
| Unsubscribe | -10 | Remove from scoring |
Sales Engagement (5 points)
| Interaction | Points | Quality Indicator |
|---|---|---|
| Booked Meeting | 5 | Highest intent |
| Answered Call | 3 | Engaged prospect |
| LinkedIn Connection | 2 | Relationship building |
| Voicemail Response | 2 | Some interest |
| No Response | 0 | Continue nurture |
Negative Scoring Factors
Deduction Triggers
| Factor | Points Deducted | Reason |
|---|---|---|
| Generic Email Domain | -5 | Personal email (gmail, yahoo) |
| Competitor | -10 | Competitive research |
| Student Domain | -8 | Academic only |
| No Company Info | -5 | Incomplete profile |
| Bounced Email | -15 | Invalid contact |
| Marked as Spam | -20 | Negative engagement |
| Job Seeker Behavior | -10 | Not a buyer |
| Geography Mismatch | -5 | Outside service area |
Decay Factors
| Time Since Last Engagement | Score Reduction |
|---|---|
| 30-60 days | -5 points |
| 61-90 days | -10 points |
| 91-180 days | -15 points |
| 180+ days | -25 points |
| 365+ days | Reset to 0 |
Advanced Scoring Models
Predictive Scoring Elements
Machine Learning Inputs
Features = {
'demographic': [title_score, dept_score, experience],
'firmographic': [revenue, employees, industry],
'behavioral': [page_views, time_on_site, return_visits],
'engagement': [email_opens, clicks, downloads],
'temporal': [recency, frequency, consistency],
'social': [linkedin_activity, referral_source],
'technographic': [current_tools, tech_stack_size]
}
Conversion Probability Model
P(Conversion) =
0.25 × Demographic_Score +
0.20 × Firmographic_Score +
0.30 × Behavioral_Score +
0.15 × Engagement_Score +
0.10 × Recency_Factor
Account-Based Scoring
Account Level Scoring | Factor | Weight | Calculation | |--------|--------|-------------| | Total Contacts | 20% | Sum of all contact scores | | Seniority Mix | 25% | Weighted average by title | | Engagement Depth | 30% | Unique engaged contacts | | Buying Committee | 25% | Multiple departments |
Contact Score within Account
Intent Data Integration
Third-Party Intent Signals | Signal Source | Points | Reliability | |---------------|--------|-------------| | G2 Research | 8 | High | | Topic Searches | 6 | Medium | | Competitor Research | 7 | High | | Community Activity | 4 | Medium | | Review Sites | 5 | Medium |
Implementation Guide
Phase 1: Basic Scoring (Week 1-2)
Setup Checklist - [ ] Configure CRM fields for scoring - [ ] Map existing data to scoring criteria - [ ] Set up basic demographic scoring - [ ] Create firmographic rules - [ ] Test with historical data
Initial Rules
Basic_Score =
CASE
WHEN title LIKE '%CEO%' THEN 15
WHEN title LIKE '%VP%' THEN 12
WHEN title LIKE '%Director%' THEN 9
ELSE 3
END +
CASE
WHEN employees > 1000 THEN 10
WHEN employees > 100 THEN 7
ELSE 3
END
Phase 2: Behavioral Tracking (Week 3-4)
Implementation Steps 1. Install website tracking 2. Configure email tracking 3. Set up activity logging 4. Create engagement rules 5. Test score calculations
Tracking Code Example
// Website Activity Tracking
function trackLeadActivity(action, value) {
leadScore.update({
action: action,
value: value,
timestamp: new Date(),
sessionId: getSessionId()
});
if (action === 'pricing_view') {
leadScore.add(5);
} else if (action === 'demo_request') {
leadScore.add(4);
}
}
Phase 3: Automation (Week 5-6)
Workflow Automation
Lead_Score_Workflow:
trigger: score_change
conditions:
- if: score >= 80
then:
- assign_to_sales
- send_hot_lead_alert
- create_task_immediate_followup
- if: score >= 60 AND score < 80
then:
- add_to_sales_queue
- send_warm_lead_notification
- if: score >= 40 AND score < 60
then:
- add_to_nurture_campaign
- schedule_check_in_30_days
Phase 4: Optimization (Ongoing)
Performance Monitoring - Weekly score distribution analysis - Monthly conversion rate by score - Quarterly model accuracy review - Continuous threshold adjustment
A/B Testing Framework | Test | Variable | Hypothesis | Duration | |------|----------|------------|----------| | Test 1 | Title weight | C-level 15→18 points | 30 days | | Test 2 | Behavior decay | 30→45 day threshold | 45 days | | Test 3 | Email weight | Reduce from 10→7 | 30 days |
Scoring Workflows
Hot Lead Workflow (80+ Points)
graph LR
A[Lead Scores 80+] --> B[Instant Alert to Sales]
B --> C[Assign to Rep]
C --> D[Call Within 5 Minutes]
D --> E{Connected?}
E -->|Yes| F[Discovery Call]
E -->|No| G[Email + Voicemail]
G --> H[Retry in 2 Hours]
F --> I[Schedule Demo]
Lead Routing Rules
Round Robin with Scoring
def assign_lead(lead):
if lead.score >= 80:
rep = get_available_senior_rep()
priority = "URGENT"
sla = "5 minutes"
elif lead.score >= 60:
rep = get_next_available_rep()
priority = "HIGH"
sla = "1 hour"
elif lead.score >= 40:
rep = get_sdr()
priority = "NORMAL"
sla = "24 hours"
else:
rep = None
priority = "NURTURE"
sla = "Automated"
return assign(lead, rep, priority, sla)
Score-Based Email Campaigns
| Score Range | Campaign Type | Frequency | Content Focus |
|---|---|---|---|
| 80-100 | Personal Outreach | Daily | Custom, value-specific |
| 60-79 | Semi-Personalized | 2x/week | Industry-specific |
| 40-59 | Automated Nurture | Weekly | Educational |
| 20-39 | Newsletter | Bi-weekly | Thought leadership |
| 0-19 | Minimal Touch | Monthly | Company updates |
Reporting & Analytics
Score Distribution Dashboard
Current Distribution
Score Range | Count | % of Database | Conversion Rate
80-100 | 234 | 2.3% | 42%
60-79 | 567 | 5.6% | 24%
40-59 | 1,234 | 12.2% | 12%
20-39 | 3,456 | 34.1% | 5%
0-19 | 4,632 | 45.8% | 1%
Score Effectiveness Metrics
Model Performance KPIs - Precision: 85% (correctly predicted conversions) - Recall: 78% (captured all conversions) - F1 Score: 0.81 - AUC-ROC: 0.89 - Lift: 3.2x over random
Score Movement Analysis
Average Score Progression
Week 0: Initial Score: 25
Week 1: +8 points (content engagement)
Week 2: +12 points (demo request)
Week 3: +15 points (pricing page)
Week 4: +20 points (sales interaction)
Week 5: Conversion at 70 points
Best Practices
Do's
✅ Review and adjust scores monthly based on conversion data
✅ Align scoring with sales feedback
✅ Test different weight combinations
✅ Include both positive and negative signals
✅ Document score calculation logic
✅ Train sales team on score meaning
✅ Use scores for prioritization, not elimination
✅ Combine individual and account scoring
Don'ts
❌ Set and forget scoring rules
❌ Ignore scores below threshold
❌ Over-complicate initial model
❌ Change multiple variables at once
❌ Rely solely on demographic data
❌ Exclude sales team from design
❌ Make dramatic score changes
❌ Ignore data quality issues
Troubleshooting Guide
Common Issues & Solutions
Issue: Score Inflation - Symptom: Too many high scores - Cause: Points too generous - Solution: Reduce point values by 20%
Issue: Poor Conversion Correlation - Symptom: High scores not converting - Cause: Wrong factors weighted - Solution: Analyze converted leads, adjust weights
Issue: Sales Ignoring Scores - Symptom: Low adoption - Cause: Lack of trust/understanding - Solution: Training + success stories
Issue: Static Scores - Symptom: Scores don't change - Cause: No behavioral tracking - Solution: Implement activity scoring
Advanced Configurations
Industry-Specific Adjustments
SaaS B2B Model - Emphasize trial activity (+10 points) - Track feature usage (+5 per feature) - Monitor integration interest (+8 points)
Enterprise Model - Weight company size higher (×1.5) - Multi-stakeholder bonus (+5 per contact) - RFP download (+15 points)
SMB Model - Faster decay rate (60 days) - Price sensitivity indicators - Self-service preference (+5)
Seasonal Adjustments
| Quarter | Adjustment | Rationale |
|---|---|---|
| Q4 | Increase urgency signals | Year-end buying |
| Q1 | Weight budget indicators | New budgets |
| Q2-Q3 | Standard scoring | Normal buying |
Integration Requirements
CRM Integration
{
"fields_required": [
"lead_score",
"score_date",
"score_category",
"score_breakdown",
"last_score_change"
],
"workflows": [
"score_calculation",
"lead_assignment",
"alert_notification"
],
"sync_frequency": "real-time"
}
Marketing Automation Integration
- Trigger score updates on activity
- Pass scores for segmentation
- Update campaigns based on score changes
- Track score influence on conversion
Analytics Platform Integration
- Daily score distribution
- Conversion analysis by score
- Score component breakdown
- Predictive model training data
Lead Scoring Model Version: 1.0
Last Updated: 2024
Review Frequency: Monthly
Model Accuracy: 85%