Lead Scoring Model Weight Tuner
Tune lead scoring model weights for demographic, firmographic, behavioral signals. Enter values for instant results with step-by-step formulas.
Worked Examples
Example 1: B2B SaaS - Balanced Model
Problem:SaaS company selling to mid-market. Current MQL-to-SQL: 20%. Sales complains about lead quality. Need to tune scoring weights.
Solution:Current Model Analysis:\n- Heavy demographic weighting (50%)\n- Light behavioral weighting (20%)\n- Result: High-fit leads passed regardless of buying intent\n\nRecommended Rebalance:\n- Demographic: 25% (was 50%)\n- Firmographic: 30% (was 30%)\n- Behavioral: 35% (was 20%)\n- Engagement: 10%\n\nKey Signals to Amplify:\n- Demo request: 90 points (strong intent)\n- Pricing page visit: 70 points\n- Case study download: 50 points\n- Blog visit: 10 points\n\nKey Signals to Add:\n- Multiple stakeholders engaging: +30 points\n- Return visits within 7 days: +20 points\n- Video completion >80%: +15 points\n\nExpected Outcome:\n- MQL volume: -15% (fewer but better)\n- MQL-to-SQL: +40% (20% → 28%)\n- Net qualified leads: +10%
Result:Behavioral weight 20% → 35% | MQL-to-SQL 20% → 28% | Quality > Quantity
Example 2: Enterprise Sales - High Threshold
Problem:Enterprise software with $100K+ deals. Sales team is small and can only work 50 leads/month. Need high-quality, sales-ready leads only.
Solution:High-Threshold Model:\nBase threshold: 75 points (high bar)\n\nFit Criteria (50% weight):\n- C-level title: 90 points\n- VP title: 70 points\n- Director: 50 points\n- Fortune 500: 30 bonus points\n- Target industry: 20 points\n- Company size >1000: 20 points\n\nIntent Criteria (50% weight):\n- Demo request: 100 points (auto-qualify)\n- Pricing inquiry: 80 points\n- Multi-page pricing visit: 60 points\n- ROI calculator use: 50 points\n- Case study (same industry): 40 points\n\nDisqualifiers:\n- Company size <200: -50 points\n- Non-decision maker: cap at 50 points\n- Competitor domain: -100 points\n\nResult:\n- Monthly MQLs: 50 (manageable for team)\n- Conversion rate: 40% (vs 15% before)\n- Deals closed: 20/month (vs 10)
Result:75-point threshold | 40% SQL conversion | 2x deals closed
Example 3: PLG + Sales Hybrid
Problem:Product-led growth SaaS with freemium. Thousands of signups but need to identify sales-assist opportunities for enterprise upsell.
Solution:Product Usage Scoring (60% weight):\n- Active users >5: 30 points\n- Usage >3x/week: 30 points\n- Advanced features used: 25 points\n- Hitting usage limits: 40 points\n- Export/API usage: 20 points\n- Collaboration features: 25 points\n\nFit Scoring (30% weight):\n- Business email domain: 20 points\n- Company size lookup >100: 30 points\n- Pricing page visit: 25 points\n- Enterprise inquiry: 50 points\n\nNegative Scoring (10% impact):\n- Personal email: -20 points\n- No activity 14+ days: -30 points\n- Single user only: -15 points\n\nPQL Threshold: 80 points\n\nRouting:\n- 80-100: Enterprise SDR outreach\n- 60-79: In-app upgrade prompts\n- <60: Self-serve nurture\n\nResult:\n- PQL identification: 3% of signups\n- Conversion to paid: 25% (vs 5% unscored)\n- Enterprise deals: 5x increase
Result:Product usage 60% weight | 3% PQL rate | 25% conversion
Frequently Asked Questions
What is lead scoring and why does it matter?
Lead scoring assigns numerical values to leads based on attributes (who they are) and behaviors (what they do). It helps sales prioritize high-potential leads, improve conversion rates, and align marketing and sales on lead quality. Effective scoring can increase sales productivity 20-30% by focusing effort on most likely buyers.
What's the difference between fit scoring and intent scoring?
Fit scoring evaluates whether a lead matches your ideal customer profile (demographics, firmographics). Intent scoring measures buying signals (behaviors, engagement). Best practice combines both: a high-fit, low-intent lead needs nurturing; a high-intent, low-fit lead may not be viable. Prioritize leads high on both dimensions.
How do I determine the right weights for scoring factors?
Start with hypothesis based on sales experience, then validate with data. Analyze closed-won deals: which attributes and behaviors correlate with conversion? Use regression analysis if you have sufficient data. Iteratively tune weights based on feedback from sales on lead quality and conversion results.
How do I handle negative scoring?
Subtract points for negative signals: competitor employees, students, job seekers, unsubscribes, spam complaints, long inactivity. Common approach: -10 for competitor domain, -5 for generic email, -20 for unsubscribe. Negative scoring prevents inflated scores from leads who will never buy.