In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

Utilization of a machine learning algorithm to support retail chain store location decisions

Authors: Petr Grin*, University of Northern Iowa
Topics: Business Geography
Keywords: geomarketing, machine learning, business location analysis
Session Type: Paper
Presentation File: No File Uploaded

Businesses use GIS (geomarketing methods) to maximize profit when searching for places to open new factories, shops, restaurants, or expand chain of cafes. The main approach of geomarketing is to calculate the optimal location based on socio-economic data, as well as on the criteria that are necessary for this type of business (suitability model).
Traditionally the Maxent model, a type of an ecological niche model (ENM), helps to make a forecast regarding the distribution of different species of animals or plants in biological science. This machine-learning algorithm uses data from points where the phenomenon in question has already been found and selects locations with similar characteristics.  Thus, the location is not determined by the expert choice, based on the conditions and factors that are perceived as necessary or beneficial, but on the basis of the conditions known for those points in which these species of animals or plant. However, this model has already been used not only to predict the location of biological species but also to predict and find potential distributions for human structures, such as wind turbines.
This pilot study tests the opportunities of using Maxent for geomarkering applications, specifically determining the ‘best’ locations for fast food chain restaurants using Taco Bell locations in Iowa as an example. The results indicate that Maxet and EMN principles could be potentially useful for geomartking applications. The resultant pilot model used a very limited number of variables but was able to demonstrate in principle the utility of the method.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login