A New Efficient Machine Learning Algorithm to Solve Facility Location Selection Problem of Geoinformatics

The problem of selecting store locations has received increased attention in the literature during the past decade, and varieties of models have been promoted to select those sites. In this paper, we address the problem of finding the optimal deployment of site locations in a certain geographic area with a given wide range of factors affecting decision making. This problem is complex and should be tackled as a multiple-objective problem. The combination of several criteria in the selection of store location must be considered. It should be noted that facility location problems require knowledge of a key parameter, “aggregated degree of importance” (ADI) indicator. This is where the discrete inverse problems can help. In this article, we discuss existing models on this problem and sketch how inverse problems (IP) can be formulated to yield a smooth ADI indicator surface. The latter is very useful both in the accurate locating of facilities as well as in computing sensitivities. A computational analysis on a non-spatial and spatial data set describing the algorithm in the site selection problem illustrates the effectiveness of the approach. Application of the facility location model is demonstrated using an example of a drug store’s selection problem in a given area.