Store clustering: how to meaningfully categorise different store types to help expansion and refurbi
  • William Beresford

Store clustering: how to meaningfully categorise different store types to help expansion and refurbi


A Leading Fast Food Chain was looking for a data-driven classification/clustering of their restaurant estate to help identify opportunities within and across their stores to generate additional ROI.

They also wanted to understand where the gaps and challenges were in their data.

Segmentation Model and Clustering

Beyond Analysis looked at a total of 132 variables to be narrowed down to 31 to build a segmentation model. Our team used a k-means algorithm which considered all of the different attributes to group the most similar restaurants together, split across 12 clusters and set out the data challenges faced and provided recommendations for addressing these in order to improve efficiency and accuracy of analysis.

Outcomes

• A filterable report where a Leading Fast Food Chain could investigate and benchmark:

- restaurant clusters, and

- restaurants within their respective clusters.

• A set of ‘pen portraits’ of each of the clusters setting out key attributes including performance, customer types

• Ability to use these clusters to optimise their estate planning operations and improve ROI. This helped to roll out EOTF and new branch openings in areas where the analysis suggested strong performance.

• A clear understanding of the gaps and challenges in the data and how to address them.


Beyond Analysis is a data science, analytics and strategic data solutions and consulting business.

Reach us at info@beyondanalysis.net

© 2020 Beyond Analysis Ltd