Scoring Module

The Scoring module audits your lead and company scoring models to ensure they're accurately identifying high-intent prospects and properly prioritizing sales outreach.

What it checks

The module runs 16 checks covering:

• Score distribution — Are scores meaningfully distributed or clustered?
• Score-to-conversion correlation — Do higher scores actually convert better?
• Stale scoring criteria — Properties used in scoring that are rarely populated
• Negative scoring gaps — Missing negative signals that should reduce scores
• Score inflation — Scores trending upward without corresponding conversion improvement
• Model coverage — Percentage of contacts with meaningful scores
• Threshold alignment — Are MQL thresholds aligned with actual conversion data?

Common findings

• Scores clustered at extremes — Everyone is scored very high or very low, losing differentiation
• No correlation between score and conversion — The model isn't predictive
• Scoring criteria based on empty fields — Properties that aren't populated can't contribute signal
• Missing negative scoring — Competitors, students, and job seekers aren't penalized

Why it matters

Lead scoring is how marketing tells sales "this one is ready." When scoring models are inaccurate, sales wastes time on low-quality leads while high-intent prospects go cold. A well-tuned scoring model is the difference between efficient pipeline generation and random outreach.