An Applied Analytics Approach for Facility Location Optimization in Logistics With Actionable Insights for Logistics Managers

Introduction

The recent advances in information technology and smart devices allow users to collect, aggregate, store, communicate, and analyze enormous pools of data, known as “big data” (Gandomi and Haider, 2015). In this digital era, data has been introduced as the new oil which needs to be refined by a combustion engine called Analytics. Facing such a tsunami of data, it is essential to apply the appropriate analytical methods to gain actionable insights and help managers making data-driven decisions (Beheshti, Benatallah, & Motahari-Nezhad, 2016). Big data analytics is revolutionizing a wide range of industries, and logistics is one of them. The complex and dynamic nature of logistics, along with the huge size of data generated by information management systems in this domain, make logistics a perfect use case for the applied big data analytics (Emrouznejad, 2016).

Big data analytics is now a reality in the logistics optimization processes since it allows supply chain managers to have data-driven decisions, based on real, accurate, and real-time information. Nevertheless, there is still a lot of work to be done, since the logistics companies are now starting to understand the full potential of the data that they have stored in their servers. This is the opportunity to develop research projects in partnership with companies so that both partners can fully use the potentials in practice.

In this industrial applied analytics research, a mathematical optimization mod-el was utilized to analyze the logistics data and detect the optimum locations for the facilities. To this end, a linear programming (LP) optimization algorithm is applied to minimize the transportation costs for the studied logistics company. The experimental results reveal that the proposed optimized model could deduct the logistics costs by 22% compared to the existing logistics network.