CHALLENGE
Getting the best location is essential for every retail, especially supermarkets, and adapting our machine learning model algorithm to the needs of the client is the main objective for Locatium. In this case, they were looking for different analyses and results of our tool, to answer the following questions:
- Where to open new stores in Iran, Egypt, and UAE?
- What are the catchment areas for the current network?
- What is the level of cannibalization?
- Capacity of each market: how many more stores to open in each country?
- What is the impact of using mobility data in addition to open data?
PROJECT DEVELOPMENT AND THE FINAL SCORE
Getting the optimal locations requires a specific prediction and the appropriate mathematical and statistical combination of our data and client internal sales data. Thanks to this, our Retail Network Tool could predict the best places with a high percentage of effectiveness We based our machine learning model algorithms on our huge data repository, which includes:
- Tracking of billions of mobile devices (which we use to do dwelling analysis, home location identification, visitation analytics, etc.)
- Tracking of billions of vehicles (which we use to do traffic on the road network, vehicle home location identification, etc.)
- Consumer Data (purchasing power, consumer profiles by category, etc.)
- Advanced Demographics (gender, income, education, nationality, etc.)
- Real Estate insights.
- Credit Card insights.
- Social Network Insights.
- Points of interest, including the location of competitors.
- At the end of the project, our client was able to see the value of our tool and the importance of the recommendations we offered, since these were obtained through in-depth mathematical analysis. They were also able to assess the quality of our data set and its accuracy based on the results that were obtained from the Locatium model. We were able to answer each of the initial questions raised.
