How to evaluate a predictive lead scoring model
Which measures answer which question, how each one misleads when read alone, and the traps that make a scoring model test well and fail in production.
17 min read
Resources
Working material for the next decision, the next check, and the next session.
CLAUDE.md
state/
condition.md
board.md
reference/
work-item.md
requires.md
execution/
skills/team/
recipes/docread/
scripts/
check_conformance.py
check_workitem.py
skill_preflight.pyThe GTM Repo
Give your agent a place to find the current state, follow the right instructions, and check its work. Start with the structure and make it yours.
See what is insideHow much CRM data do you need for predictive lead scoring?
The documented data minimums for predictive lead scoring: Einstein's 1,000-lead threshold, Dynamics' 40/40 rule, what the research used, and what actually determines whether your model works.
5 min readPredictive lead scoring under peer review: what a 2025 study gets right, and three questions it leaves open
A journal-club review of González-Flores et al. (2025), a peer-reviewed B2B predictive lead scoring study: what holds up, and the three validation questions every scoring model should face.
7 min readHow to score leads by job title - with a prompt you can run today
A configurable prompt that turns your messy job-title field into the patterns that actually predict conversion - how to read the output, follow-up prompts, and how ax1om does it at scale.
15 min read