The extrapolated_count_normalized field contains a JSON object with extrapolated and normalized visit counts across six different levels of aggregation:
- placekey_count
- Description: Raw visit count for this specific POI location
- Granularity: Individual location level
- Example: 42 visits to this specific AAA/CAA branch
- location_name_count
- Description: Extrapolated count across all POIs with the same location name
- Granularity: Location name level (all branches/locations of same business name)
- Example: 1,633 total visits across all AAA/CAA locations
- brands_count
- Description: Extrapolated count across all POIs associated with the same brand
- Granularity: Brand level (similar to location_name but may include brand variants)
- Example: 1,447 total visits across all AAA/CAA branded locations
- sub_category_count
- Description: Extrapolated count across all POIs in the same sub-category
- Granularity: Business sub-category level
- Example: 485,794 total visits across all "Insurance Agencies and Brokerages"
- top_category_count
- Description: Extrapolated count across all POIs in the same top-level category
- Granularity: Business top-category level
- Example: 471,736 total visits across all "Agencies, Brokerages, and Other Insurance Related Activities"
- naics_code_count
- Description: Extrapolated count across all POIs with the same NAICS code
- Granularity: Industry classification level (NAICS code 524210)
- Example: 492,830 total visits across all businesses with NAICS code 524210
Normalization Methodology
The counts represent extrapolated and normalized values that account for:
- Sampling bias correction: Adjusts for device penetration rates
- Temporal normalization: Standardizes counts across different time periods
- Geographic weighting: Accounts for regional population and device density differences
- Category-specific adjustments: Applies category-appropriate scaling factors