📊 Segments & Scoring
Every person in your Audience Graph receives a dynamic engagement score and is automatically placed into segments. These scores and segments drive personalization across the entire platform — from AI Auto-Reply context to Escalation Rules to Client Reports.
Engagement Scoring​
The engagementScore on each AudienceNode is a composite metric calculated from:
| Signal | Weight | Description |
|---|---|---|
| Comment frequency | High | Total comments across all platforms (totalComments) |
| DM interactions | High | Total direct messages (totalDMs) |
| Purchase history | Very High | Number of purchases (totalPurchases) and total spent (totalSpent) |
| Average order value | Medium | avgOrderValue — higher AOV increases score |
| Recency | High | Time since lastInteractionAt — recent activity boosts score significantly |
| Purchase recency | High | Time since lastPurchaseAt |
| Interaction diversity | Medium | Engaging across multiple platforms and interaction types |
Scores are updated automatically every time a new interaction is recorded. The algorithm uses a time-decay function so that recent activity is weighted more heavily than historical data.
Each AudienceInteraction logged — whether it's a comment, DM, mention, or purchase — triggers a recalculation of the parent AudienceNode's engagement score. The sentiment and intent fields on interactions also factor in: positive sentiment interactions contribute more than neutral ones.
Auto-Segmentation​
UniPulse AI automatically groups your audience into segments based on engagement score patterns and purchase behavior:
| Segment | Criteria | Description |
|---|---|---|
| Champions | High engagement + frequent purchasers | Your best customers — engage often and buy regularly |
| Loyal Fans | Consistent engagement over time | Regular interactors who may or may not purchase |
| At Risk | Declining engagement (score dropping) | Previously active customers showing disengagement signals |
| New Contacts | firstSeenAt within last 30 days | Recent first-time interactors |
| Potential Buyers | High purchaseIntentScore in conversations | Showing purchase intent signals but haven't converted yet |
| Dormant | No interaction for extended period | No activity in the lastInteractionAt window |
Segments are re-evaluated continuously. A customer can move between segments as their behavior changes.
AudienceSegment Model​
Each segment (both auto and custom) is stored as an AudienceSegment:
| Field | Description |
|---|---|
| name | Segment name (e.g., "Champions", "Holiday Shoppers") |
| description | Human-readable description of the segment's purpose |
| rules | JSON array of rules that define membership (see below) |
| memberCount | Current number of audience nodes in this segment |
| isAutomatic | true for AI-managed segments, false for custom segments |
Custom Segments​
Create your own segments in Audience > Segments > New Segment based on any combination of criteria:
| Criterion | Examples |
|---|---|
| Engagement score | Score > 80, Score between 40–70 |
| Platform | Only Instagram followers, Only TikTok commenters |
| Interaction type | Has sent a DM, Has commented more than 5 times |
| Purchase data | Total spent > $100, Has purchased in last 30 days |
| Tags | Has tag "VIP", Does not have tag "Unsubscribed" |
| Tier | Customer tier is "Premium" |
| Location | Based on available profile data |
| Sentiment | Average sentiment across interactions is positive |
| Time-based | First seen before a specific date, Last interaction within X days |
Rules are defined as JSON and support AND/OR logic for complex combinations.
Using Segments Across UniPulse​
Segments are a powerful building block used throughout the platform:
| Feature | How Segments Are Used |
|---|---|
| AI Auto-Reply | Personalize bot responses based on customer segment |
| Escalation Rules | Trigger escalation when a VIP or Champion customer contacts you |
| Client Reports | Generate segment-specific performance reports |
| Content targeting | Prioritize content for specific audience segments |
| Coupon generation | Auto-generate personalized coupons for at-risk or high-value segments |
Related Pages​
- Audience Graph — The profiles that segments are built on
- Cross-Platform Identity — How unified profiles enable accurate scoring
- Escalation Rules — Use segments as escalation conditions
- Client Reports — Report on segment-level performance