Hunker, J.; Scheidler, A. A.; Rabe, M.: A Systematic Classification of Database Solutions for Data Mining to Support Tasks in Supply Chains. In: Kersten, W.; Blecker, T.; Ringle, C. M.: (eds.): Data Science and Innovation in Supply Chain Management: How Data Transforms the Value Chain. Proceedings of the Hamburg International Conference of Logistics (HICL) Hamburg, 24.-25. September 2020. Berlin: epubli GmbH, pp. 395-425.

Our research shows that considering well suited NoSQL databases is ben-eficial for logistics tasks. For answering tasks we rely on the widespread methods of Data Mining. We stress that using relational databases as basis for Data Mining tools cannot cope with the growing amount of data and that using NoSQL databases can be an important step to address these issues. Methodology: This paper discusses Data Mining in the context of Supply Chain Man-agement tasks in logistics and its requirements on databases. The paper demon-strates that using NoSQL databases as basis for Data Mining process models in logis-tics is a very promising approach. The research is based on a case study, whose core element is the analysis of different well established studies. Findings: The paper presents results which show that Data Mining tools widely sup-port NoSQL databases through available interfaces. Findings are presented in a com-parison table which considers dimensions such as Data Mining tools and supported NoSQL databases. To show practical feasibility, a Data Mining tool is used on data of a Supply Chain stored in a NoSQL database. Originality: The novelty of this paper emerges from addressing issues that have so far been insufficiently analyzed in the scientific discussion. The modular structure of the addressed research method ensures scientific traceability. Breaking down tasks and their requirements on databases in the field of Data Mining is a first step towards meeting trends like Big Data and their challenges.