Geospatial Data to Optimize Supply Chains

Through geospatial data analysis techniques, CentralAmericaData carried out an analysis of five Walmart distribution centers in Florida, United States, with the aim of identifying patterns in the supply chains of these five centers and their relationships with commercial establishments and other logistics complexes in the State.

Thursday, July 8, 2021

Through this analysis, whose objective is to show how geospatial data science techniques can be applied to solve problems in the logistics sector, the existing relationships between Walmart distribution centers and their supply sites were identified and characterized, so that different large commercial chains can evaluate and at the same time improve processes in their respective supply chains.

How was it done?

Hundreds of thousands of mobile device records in the areas where Walmart distribution centers are located were analyzed. This cellular positioning data, which is obtained for a specific location and time period, when analyzed on a large scale, provides insight into the influx of people at each point of interest, in this case, the distribution centers and other commercial establishments in the area in question.

With this information, it was possible to infer patterns of behavior in the logistics chain between the distribution centers and the locations to be supplied, establishing the delivery and reception parties with a count of mutual visits. This made it possible to pinpoint the main and most important relationships between distribution centers and stores.

You might be interested in: "Big Data to Understand Consumer Mobility."

Methodology

In order to predict and understand the visits and relationships between Walmart's distribution centers in the state of Florida and the surrounding establishments, the following was performed:

First, the state was divided into five zones: Central, North-east, Northwest, Southeast, and Southwest. Subsequently, the coordinates of the distribution centers and headquarters were defined in order to locate them on a map, establishing each center and headquarters as a registry with its respective geographic information. Using an innovative methodology of creating polygons over the buildings, the perimeters were determined, and finally, with the anonymized cell phone positioning data, it was possible to define the number of people who visited the distribution centers and a location in a given period of time.




Also see: "Big Data to Infer Relationships between Companies."

This visualization shows the relationship between distribution center square footage and visit volume. A linear regression line was included, representing a proportional growth between visits with distribution center square footage. Therefore, if the property is close to the line, it means that the distribution center space is being better utilized. With this in mind, it could be calculated that:

The size of the circle represents the number of visits. We can see that the larger the size of the perimeter of the distribution centers, the greater the number of visitors.

As can be seen, almost all facilities seem to line up close to the trend, which shows a formidable ratio between perimeter and visitor volume.

The only exception is the Alcachua center (purple circle), as it is the only spot that seems to be wasting its space capacity. Although it does not rank last in terms of floor space, it is the center with the least footfall.

This type of model helps organizations to identify and characterize the direct relationships that exist between relevant variables such as physical space and foot traffic at each point, which becomes a highly valuable input for finding trends and optimizing processes in supply chains.

Do you know that we are now part of something bigger?
Learn about PREDIK Data-Driven, our new global brand.

Do you need more information about this type of solutions? Contact us.









this site is protected by reCAPTCHA and Google's privacy policy and terms of service.
Need assistance? Contact us
(506) 4001-6423


More on this topic

Footfall analytics: Walmart Supercenter Vs. Kroger

December 2021

Supermarkets can apply location intelligence techniques and footfall analytics to understand consumer mobility patterns, generate efficient site selection strategies, understand the performance of their stores, and estimate competitor turnover.

The correlation between foot traffic visitation, sales, and the success of retail supermarkets have been studied and proven, so the development of this type of analysis has become a priority in the site selection process and expansion modeling.

Walmart Vs. Soriana: Consumer Foot traffic Analysis

August 2021

Mobility data analytics are transforming the way commercial strategies are defined in the retail business, and supermarket chains are no exception.

Understanding what consumers think, what they want and what they do is critical for companies in the retail sector. This is where Big Data tools play an important role, as it is possible to measure the affluence at a location and customer behavior, among other aspects.

Data Science to Analyze Relationships between Companies

July 2021

Big data has currently become one of the newest allies to infer relationships between companies, competitors and suppliers, since the analysis of large volumes of data can reveal missing or relational aspects between different sectors within organizations, where they can complement each other.

The set of networks in which companies participate are considered as a resource for them.

Big Data to Infer Relationships between Companies

July 2021

By analyzing the large volumes of anonymous data generated by mobile devices, it is possible to establish whether a distribution center has a commercial relationship with other logistics complexes, and even with establishments that serve the end consumer.

Using the most advanced Big Data tools, it is possible to understand the behavior of the supply chains of companies in the retail sector, since by monitoring delivery parts and counting mutual visits between suppliers and vendors, it is possible to identify and establish which are the most important relationships between distribution centers and points of sale to the end consumer, such as stores.