Use of Big Data Analysis to identify possible sources of Supply Chain disruption through the DOTMLPFI method

Backgrounds: The presented research deals with the investigation of how big data analytics can help predict possible disruptive events in supply chains. The supply chain can be considered a complex system with a wide spectrum of possible sources of internal and external disruptions. Since the individual entities of the supply chains operate in a particular environment and interact with this environment, there is a certain level of mutual interdependency. This set of interconnected interactions within the supply chain will be the unit of analysis. Methods: There are many internal and external sources of supply chain disruption, which opens up the potential application of Big Data Analysis (BDA) as an early warning tool. To analyse the possible application of the BDA to identify sources of supply chain disruptions, we conduct a bibliometric analysis to define an appropriate structure for supply chain risk classification as well as appropriate keywords that make data collection quicker and easier. The DOTMLPFI methodology was used to systematically identify the most relevant risks threatening the supply chains. Results: The proposed research approach creates a possible framework to support the operational sustainability and resilience of the supply chain as a system, toward internal and external disruptions. The research results also point out the most explored attributes of supply chain disruption. The conducted bibliometric research and content analysis support the theoretical framework of using BDA as a possible early warning tool, especially for the identification of possible sources of supply chain disruption. The approach of grouping Big Data sources into categories based on DOTMLPFI groups allows to identify the appropriate keywords for their later BDA analysis. The analytical framework provides a starting point for individual supply chain entities to understand risks and systematically collect the appropriate data in the required structure about them. Conclusion: The complexity of supply chains, together ...