Geospatial · Areas and surfaces

Gravity Model

Splits each area's demand between the locations in range by their attractiveness and distance (the Huff model). Gives the demand each location captures, such as a new store's sales and what it takes from the others, the top location per area, or a probability for every area and location.

Also known as: Huff model, market share, site selection

How it works

Wire the demand table (origins such as census blocks) into the first input and the locations (your stores and competitors) into the second. Pick the Demand geometry column, an optional Demand column (blank means every origin counts 1), the Locations geometry column, the Location id column and an optional Attractiveness column (blank treats every location as equal). Distance measure is Straight line by default; Drive time and Drive distance need routing tiles and a Travel mode. Locations beyond the Search limit (30 km by default, minutes under Drive time) are ignored.

Each origin's demand is split by the Huff model: probability = attractiveness^α × decay(distance) / sum over locations in range, with Distance decay set to Power (the default, exponent β = 2) or Exponential, and the Attractiveness exponent α (1). Output picks the shape: Location summary adds captured_demand, market_share and origins_reached to each location; Origin summary adds top_location, top_probability and locations_in_range to each origin; Pairs (origin × location) gives one row per pair with location_id, distance_km (travel_minutes under Drive time), probability and expected_demand. α, β and the search limit can also be bound to a params table from Calibrate Gravity Model.

Inputs and outputs

Settings

{
  originGeometryColumn: string
  demandColumn?: string
  locationGeometryColumn: string
  locationIdColumn: string
  attractivenessColumn?: string
  distanceMeasure: "straight"|"drive-time"|"drive-distance"
  decay: "power"|"exponential"
  alpha: number
  beta: number
  searchLimit: number
  output: "locations"|"origins"|"pairs"
  costing: "auto"|"bicycle"|"pedestrian"|"truck"
}

Example

For a candidate site, Union it onto the locations table, run with Location summary, and compare captured_demand per store against a run without it to see what the new site takes from each store.

More in Areas and surfaces

• Trade Areas — Builds catchment areas around each location: distance rings, drive-time bands, areas traced from demand, or rings cut into sectors.
• Calibrate Gravity Model — Fits the Gravity Model's attractiveness and distance-decay settings to what customers actually did, such as loyalty-card visits per area and store, and reports how well the fit reproduces each store.
• Voronoi — Draws one area per point covering everywhere closer to it than to any other point, such as the nearest-store territory for every shop.
• H3 Aggregate — Puts features into hexagon cells of a chosen size and summarizes each cell, for an even grid on density maps.
• Spatial Interpolate — Estimates a smooth surface from measured sample points, on a hexagon or square grid. For example, a pollution surface from sensors.