Which shopping center should I choose to open my store?

The key to attracting potential customers to any new location is to determine its foot traffic potential, the use of geospatial data combined with footfall analytics makes the retail site selection process easier, faster, and more reliable.

At PREDIK Data-Driven we support corporations by optimizing their site selection strategies with 100% data-driven methodologies. One of our clients, a major regional footwear retail corporation, was able to determine in which shopping mall it was more convenient to open its first brick and mortar store, thus reducing investment risks and maximizing its revenues, having identified its potential customers and its target market in the malls.

CASE STUDY: LOCATION INTELLIGENCE APPLIED TO THE LOCATION STRATEGY AT SHOPPING MALLS FOR A FOOTWEAR RETAIL STORE

PROBLEM TO BE ADDRESSED

The company, dedicated to the commercialization of footwear articles, needed to identify the most suitable shopping malls for the opening and management of its first point of sale since it only had virtual stores.

BUSINESS INTELLIGENCE SOLUTION

At PREDIK Data-Driven we developed a probabilistic model that collects geographic, demographic, and subjective information about preferences and interests of potential customers of the store, we analyzed the in-store mobility of the malls and around them, we identified potential competitors, and we made a forecast of the sales potential of the store within each of the shopping centers.

METHODOLOGY AND DATA SOURCES USED FOR THE ANALYSIS

The methodology used for the development of this solution consisted of the collection, cleansing, homologation, validation, and analysis of all information from secondary and third-party sources, including, but not limited to:

  1. Geographic information of the environment of the shopping centers such as:
  • Floating population data interested in footwear items and shoe brands.
  • Positioning data from mobile devices that registered a visit to the malls.
  • The identification of competitors in the malls.

2. Processing and analysis of data from the target audiences in social networks that visit the shopping malls, allowed us to determine the profile of visitors and those who interact with the topics most related to the store.

3. Processing and analysis of data from mobile device positioning records of more than 2,000,000 users in the city of interest, allowed us to identify at a more detailed level the visitors’ characteristics of the shopping centers, based on the identification of their in-store and surrounding foot traffic patterns.

4. At this point we already know the potential customer of each shopping center, as well as the general characteristics of the visitors (interests, relative wealth index levels, other preferred points of interest visited, distribution of visits by day and time, etc.)

5. In order to obtain an estimate of potential sales, it was necessary to have customer information such as:

  • Average ticket of sales registered online.
  • Recorded sales history in the city of interest.
  • Visits to the online store coming from the city.
  • Location of customers according to product delivery places.

Although we do not have evidence of a physical store’s sales, this information from the online channel will allow us to understand the buying patterns of customers in the city of interest, and therefore be able to shape the annual sales in each shopping mall, based on the potential buyers that we observe and the existing competition in the mall.

Note: All images were used only for illustrative purposes, taken from prototypes made by the PREDIK Data-Driven team.


Like what you see? Request a Free DEMO