Data Mining in Logistics – Choice or Challenge?

Abstract:

The article is focused on the identification of data mining logistics processes and describing them. The development of digital technologies such as Web 2.0, Internet of Things, and Industry 4.0 (Govindan, Cheng, Mishra, Shukla, 2018) resulted in data mining gaining more attention nowadays. The article indicates theoretical aspects of data mining and relates to numerous examples of data mining usage in logistics (especially in transport and supply chain management) described in literature and papers. Logistics, as a data-driven branch of science (Lekić, Rogić, Boldizsar, Zoldy, Torok, 2019) can significantly benefit from introducing operations on large datasets. The main aim of the article is to identify examples of logistics operations that were possible to introduce because of the data mining application and therefore, synthesize theoretical, conceptual, and empirical literature in which data mining procedures are used as logistics tools, from the general to the specific. The set goal is accompanied by the following research questions: What are the potential challenges in using more data mining operations in logistics? The systematic literature review method was used to identify the literature on data mining in logistics. The research was carried out following the methodology described in the publication of  Tranfield, D., Denyer, D., Smart, P., Towards a Methodology for Developing Evidence-Informed Management Knowledge by Means of Systematic Review, 2003, British Journal of Management 14(3), pp. 207-222. The author conducted research in 3 stages, i.e. defining the plan of the literature review and main aim of the research, selecting publications, and analysing the content. Full-text foreign databases such as Springer Nature Journals, Web of Science were analyzed.  The author concluded the article by developing a summary of examples described and suggesting the possible direction of future research.