Heap's approach to developing a predictive health score model for customer success involved leveraging data from Heap, Salesforce, and Catalyst to provide timely and reliable information that informs revenue forecasting and optimizes resource allocation. The model, spearheaded by Lane Hart, incorporates leading indicators of success and uses a segmented customer approach to tailor experiences based on digital footprints. By organizing health score factors into adoption and relationship buckets, Heap improved the accuracy and reliability of its health predictions, resulting in over 95% accuracy in renewal forecasts. The process involved a six-month data collection period without alterations to ensure the validity of the metrics. As a result, the post-sales team saved time by reducing manual data analysis and increased confidence in decision-making through prescriptive playbooks. The iterative process also included refining the operating cadence to enhance efficiency, with a cross-functional team reviewing customer journeys and health scores to align on strategies for renewals and expansions. This structured approach not only improved forecast accuracy but also allowed the team to reallocate hours towards customer-facing activities.