Our team at YuzuData is constantly building new derived data products
Most data out there is sold like "raw ingredients", where you need to do a lot of processing and data engineering to get any value out of it.
One of the pillars of Last Mile Data Intelligence is that the data you start with when doing some analysis, should be as close to the use case as possible.
Thus we began building custom datasets to act less like raw ingredients and more like meal kits for your location analysis.
Brand Suitability Dataset
To build the Brand Suitability Dataset, we started by building a machine learning model that determines key location characteristics associated with a retail brand's store location strategy. With this we were able to create a neighborhood "signature" of what kinds of markets that brand prefers. We then used that signature to rank every census block group in the US based on its similarity to that profile.
Thus, you can use this dataset to pull up a particular neighborhood and identify the top retailers that are not already there but that are a good match for that market.
In building our analysis pipeline for our Brand Suitability Dataset we ran into an unexpected problem: we needed to know the open dates of a brand’s stores and couldn’t find this data anywhere.
It wasn’t readily available in standard POI datasets, or even commercially produced location-scraping POI datasets.
So our team at YuzuData created our own version.
It’s accurate to the year and quarter a store location opened. So for example, you might pull up Starbucks 3 different Starbucks locations and see that one was opened in Q1-2020, one in Q4-2023, one in Q2-2021.
Our Grocery Accessibility Dataset started as a side project where we wanted to evaluate food deserts across America. As often happens with side projects in this industry, before we knew it we had a dataset worth putting out into the world.
About The Dataset
→ This data product provides a region’s grocery store accessibility as a single score.
→ Organized in the H3 spatial indexing system at hex resolution 8.
→ US version is being created first with a global version to follow shortly after.
→ Can be used either in manually/visually assessing a region or as an input for geospatial models.
Our logistics-focused customers know how important it is to be near a highway on-ramp and off-ramp. Depending on the business, it can play a major role in a company's location strategy. Thus we produced this dataset to ease in making that decision.
About The Dataset
→ Organized in the H3 spatial indexing system at hex resolution 8.
→ US version is being created first with a global version to follow shortly after.
→ Can be used either in manually/visually assessing a region or as an input for geospatial models.
