Agentic AI & AutomationMarketing Glossary

Propensity Model

A propensity model is a machine learning model that predicts the likelihood of a specific behavior — purchasing, churning, upgrading — based on historical data patterns. More sophisticated than simple lead scoring, propensity models find non-obvious correlations (companies that have a specific tech stack, hired recently, and visited your site 3+ times are 8x more likely to close). They're increasingly accessible through tools like MadKudu and 6sense.

Real-World Example

For example, a propensity model trained on your closed-won deals might identify that companies using Salesforce + Gong with a >100 employee sales team and recent SDR job postings have 40% higher win rates — letting you prioritize those accounts over generic ICP fits.

At Cactus

For clients with sufficient historical deal data, we build propensity models that dramatically improve outbound prioritization — focusing human SDR time on accounts most likely to close.

Want help applying this?

We implement Propensity Model strategies for B2B tech startups every day. Book a free 30-minute call to get a concrete plan for your situation.

Book a free strategy call →