Site selection · SDSS
Score a city with weighted criteria, forecast the shortlist with a calibrated Huff model, measure cannibalization and read the catchment — all in one scenario you can save and share.
Population density, income, daytime population, traffic, growth, competition, complementary businesses, rent and demand gap are min-max normalized across the city. Rent and competition are inverted, so lower is better. Weights from 0 to 10 combine them into a 0–100 score per hexagon.
For a candidate location, the model computes each hexagon’s probability of choosing every store in the category, including an outside option. A calibration factor fitted to observed visits turns modeled demand into daily and annual visit forecasts.
The same model is run before and after the opening. The difference at each existing store is the cannibalization — reported in daily visits and percent, with distance, so you can see what is net new.
Rings in miles, kilometers or drive minutes, with demographics aggregated by the share of each hexagon inside the ring, plus segments and the business mix.
Yes. The methodology page publishes the Huff probability, calibration, cannibalization, normalization and aggregation formulas exactly as implemented.
Drive minutes are converted to a radius using each city’s average driving speed. It is a fast approximation, not a road-network isochrone, and the docs say so.
Each successful suitability, Huff, catchment or compare-sites run counts as one analysis toward the plan’s monthly limit.
Start free with the demo cities, or book a walkthrough with our team.