QuIS: The Question of Intelligent Site Selection

TL;DR

The paper introduces QuIS, an automatic, scalable, and explainable method for site selection that outperforms existing approaches by analyzing comprehensive location data and providing actionable recommendations.

Contribution

It presents QuIS, a novel approach for site selection that is automatic, scalable, and offers explanations, improving decision-making over manual and subjective methods.

Findings

86.4% coverage with existing supermarket sites

Recommends 328 new potential supermarket sites

Identifies new decisive location factors

Abstract

Site selection is one of the most important decisions to be made by companies. Such a decision depends on various factors of sites, including socio-economic, geographical, ecological, as well as specific requirements of companies. The existing approaches for site selection are manual, subjective, and not scalable. The paper presents the new approach QuIS for site selection, which is automatic, scalable, and more effective than existing state-of-the-art methods. It impartially finds suitables site based on analyzing decisive data of all location factors in both time and space. Another highlight of the proposed method is that the recommendations are supported by explanations, i.e., why something was suggested. To assess the effectiveness of the presented method, a case study on site selection of supermarkets in Germany is performed using real data of more than 200 location factors for 11.162 sites. Evaluation results show that there is a big coverage (86.4 %) between the sites of existing supermarkets selected by economists and the sites recommended by the presented method. In addition, the method also recommends many sites (328) where it is benefial to open a new supermarket. Furthermore, new decisive location factors are revealed, which have an impact on the existence of supermarkets.