GeoPython 2021

How to Use Spatial Data to Identify CPG Demand Hotspots
2021-04-22, 10:15–10:45, Track 1

Spatial models can provide a rich set of tools to analyze multivariate geolocated data, enabling data-driven decisions to understand consumer behavior in the CPG industry.

Spatial data from a variety of sources are increasingly used to target marketing campaigns and prioritize rollout to an optimal audience. In this talk, we will demonstrate how different data sources (e.g. geosocial segments, internet searches, credit card data, demographics and point of interest data) can be blended and how spatial models can be used in identifying “demand hotspots” for Consumer Good Products (CPG). First, I will walk through a methodology on how to select target audiences in New York and Philadelphia for organic / natural products, based on spatial analysis of factors from the different datasets. I will then show a statistical analysis on how features for elimination purposes take place and a classifier is built to examine the impact of each factor on the selection of the “demand hotspots”. I will also present how the conclusions can be extrapolated for further locations, making use of a similarity score index which is based on probabilistic principal components analysis.