APPROACH

We addressed the client’s challenge in a 5-step process:

  • We used an electronic design automation of representative stores to hypothesize the structural variables in the analysis.
  • We built classification tree to identify key structural variable impacting the sales in the stores.
  • The outliers stores were then removed through clustering of the existing stores based on key structural variables such as population density, big box retailers, and eateries, controlling the impact of executional variables.
  • This was followed by a regression to understand key drivers for each cluster.
  • Finally, we prioritized the variables based on their influence on store performance.

 

KEY BENEFITS

  • The web application designed for the client provided an intuitive visualization layer
  • It provided the client the flexibility to apply any prospect location, in return giving him a gross addition forecast in near real-time.
  • The solution fetches real-time information from diverse platform such as Google and Yelp

RESULTS

Our integrated solution reduced the manual efforts involved in the research and investigation of new locations, from many man hours to just under a few minutes

The client could now identify the most optimum location for the new stores supported by insights based on statistical techniques.

Drill down ability of the solution, to point the best possible location within a given territory, further reduced the decision making time and efficiency of the territory managers.