Stable
📈 Live history is activating for this object — the automated backfill is in progress.
⌁ mcp.call("adw-203") v1.0 ← All products
Retail/Marketing · Index Paid
Wallet-Share Erosion
Identify high-value customers at risk of churning to specific competitors to enable targeted retention campaigns and recover lost revenue.
- Refresh
- daily
- History
- single vintage
- Plan
- Paid
Forward outlook
Prediction
- Horizon
- —
- Recommended use
- Identify high-value customers at risk of churning to specific competitors to enable targeted retention campaigns and recover lost revenue.
Methodology
How it's built
Inputs include historical transaction frequency, average basket size, and competitor price indices; apply a churn probability model weighted by price sensitivity to output an erosion risk score.
Internal loyalty program transaction logsthird-party panel data (e.g.NielsenIRI)
Version 1.0 · validated to beat a naive baseline · benchmark: needs partner data
Live response
The object an agent receives
One call returns the answer with its reasoning attached — the live Intelligence Object for ADW-203.
GET /v1/intelligence/adw-203
{} IOM schema
The agent-callable contract
Every product conforms to the Intelligence Object Model — typed, versioned, and discoverable.
- product_id
- entity
- score
- trend
- confidence
- top_drivers
- prediction_horizon
- recommended_use
- methodology_version
- freshness
- coverage
- source_lineage
- allowed_use
MCP tool: adw.adw_203
Access options
Consume it your way
-
Dashboard
Read the score + drivers in the console.
-
REST API
/v1/intelligence/adw-203
-
MCP tool
adw.adw_203
-
Marketplace
Discoverable by any MCP agent via the MCP registry.
-
White-label
Embed under your own brand (Platinum).
Plan requirement
Depth scales with the plan
- Free Sample object — current score only
- Gold Full drivers + history + confidence
- Platinum White-label + bulk + SLA
Related products
Browse all Retail/Location · Score Paid
Global Real Estate Affordability Score
How affordable is real estate vs income?
Method: 100-(Norm_Price_Income+Norm_Rent_Income)
monthly · next ~30d score 42
View object → Retail/Marketing · metric Paid
Promo-Elasticity Gap
Identify underperforming promotional investments to reallocate trade spend toward high-elasticity categories for maximum revenue lift.
Method: Calculate price elasticity of demand using historical sales volume and discount depth data, then compute the gap between actual promo ROI and the theoretical maximum ROI to generate a prioritization s
daily · next ~24h
View object → Retail/Location · Index Paid
Demographic Affinity / Site-Selection
Identify high-potential zip codes for new retail locations by matching store concepts to local population characteristics.
Method: Aggregate Census demographic variables (income, age, household size) with proprietary spending propensity scores to generate a site-fit affinity index.
daily · next ~24h
View object →