predict_moment_quality
Predict the VAS (Viewability Attention Score) a specific creative would achieve at a given moment, based on historical data and causal modeling.
Uses the CausalPredictionService which:
Embeds the moment description to find historically similar moments
If >= 5 similar moments exist with the same creative, uses weighted-average prediction
If insufficient data, falls back to Gemini generative prediction
Always decomposes the prediction into causal factors
WHEN TO USE:
Evaluating whether a creative will perform well in a specific context
A/B testing creative placement hypotheses before committing budget
Understanding which causal factors drive VAS for a creative
Comparing expected performance across different moment types
RETURNS:
prediction: { predictedVAS (0-1), confidence (0-1), method ('historical'|'model'), sampleSize }
causal_factors: { audienceMatch, contextMatch, attentionState, socialPotential } (each 0-1)
metadata: { creative_id, moment_description }
suggested_next_queries: Follow-up queries
EXAMPLE: User: "How would a coffee ad perform at a transit station during morning rush?" predict_moment_quality({ moment_description: "transit venue, morning commute, 12 viewers, high attention, mostly 25-34 age range", creative_id: "coffee-brand-morning-30s" })
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| creative_id | Yes | The creative/ad ID to predict performance for. | |
| moment_description | Yes | Natural-language description of the target moment context. Include venue type, time of day, audience size, demographics, attention level, etc. |