How Lead Scoring Works

What is Lead Scoring?

Lead scoring assigns a numerical value (0-100) to each contact based on their likelihood to convert. Higher scores indicate hotter leads that deserve immediate attention.

Factors in Lead Scoring

Our AI considers multiple signals to calculate lead scores:

• Engagement HistoryEmail opens, clicks, property views, and response rates

---

• Behavioral SignalsSearch frequency, saved properties, time on site, and viewing patterns

---

• Profile CompletenessBudget stated, pre-qualification status, timeline clarity

---

• Activity RecencyRecent interactions weighted more heavily than old ones

---

• Historical PatternsSimilar leads that converted in the past

Understanding Confidence Levels

Each lead score comes with a confidence percentage showing how certain the AI is about the score:

• High Confidence (90%+)Sufficient data points, clear patterns. Trust this score.
• Medium Confidence (70-89%)Good data but some uncertainty. Monitor for changes.
• Low Confidence (<70%)Limited data or mixed signals. Gather more information.

Why Scores Change

Lead scores are dynamic and update automatically when:

• • Contact interacts with your emails or messages
• • They view properties or save searches
• • Profile information is updated (budget, timeline, etc.)
• • Time passes without engagement (decay)
• • AI learns from similar leads that converted

Best Practices

• Focus on 85+ scores firstThese are your hottest leads with highest conversion probability
• Review 70-84 scores regularlyGood opportunities that need nurturing
• Use automation for <70 scoresSet up drip campaigns to warm them up automatically
• Check 'Why This Score' explanationsAI shows reasoning for transparency and learning
• Override when you have insider knowledgeYour expertise trumps AI—manual overrides are respected

AI Learning & Improvement

The scoring model learns from your outcomes:

• When leads convert, AI identifies patterns that preceded the conversion

• When you manually adjust scores, AI learns your preferences

• Scores become more accurate over time as the system learns your market

• Historical patterns unique to YOUR business inform future scores