We took a data-driven approach by integrating Google Location API data with macroeconomic indicators and retail potential metrics. To assess the industry landscape and identify potential customers, we analyzed a wide range of sources including Census data, retail transaction records, and geospatial insights from Google.

To estimate the size of the market opportunity, we combined traditional statistical clustering with advanced techniques like Random Forest and time series modeling to identify the main drivers of growth.

Filtering and segmentation techniques were applied to postal codes, using macroeconomic indicators to identify high-potential ZIP codes. This analysis produced a “Potential Index” that reflects purchasing power, consumption capacity, and behavioral patterns. Based on this index, we segmented the market into activation clusters, offering strategic insights to guide targeted decision-making.

We developed a multi-criterion location “Attractiveness Score” that evaluated shortlisted location clusters. This score was weighed against competitive benchmarks, including store density and ticket size, to craft a priority hierarchy of locations.