Context

Rang Technologies is preparing to deploy a binary classification model in Rang Sales Hub to score inbound leads as likely or unlikely to convert within 30 days. The model will determine which leads are routed to the SDR team first. In offline testing, the model looks better than the legacy rules-based system on ranking quality, but several validation signals suggest deployment risk.

Current Performance

The Problem

The VP of Revenue wants to launch the model next week because precision improved materially, but SDR leadership is concerned that recall dropped from 0.68 to 0.47, which could reduce total conversions if too many good leads are deprioritized. You need to determine whether the model is actually ready for deployment and what validation steps should happen before launch.

Requirements

1. Assess whether the candidate model is deployable given the metric tradeoffs.
2. Explain which offline metrics matter most for this use case and why.
3. Identify likely validation gaps or failure modes before deployment.
4. Recommend threshold, calibration, and segmentation checks.
5. Propose a go/no-go decision and a safe rollout plan in Rang Sales Hub.

Constraints

• SDR team can actively work only the top 25% of daily leads.
• Missing a true converter is estimated to cost 8x more than reviewing a false positive.
• Labels arrive with a 30-day delay, so online feedback is slow.