An analysis of critical factors for adopting machine learning in manufacturing supply chains

Abstract

This study identifies and examines the critical factors for adopting machine learning technologies in manufacturing supply chains. Initially, a thorough literature review was employed to identify 13 critical factors, and then the Decision-Making Trial and Evaluation Laboratory (DEMATEL) methodology was used to analyse their cause–effect relationship. Next, a qualitative analysis concluded that ‘Technology Integration’ and ‘Forecasting’ are essential for adopting machine learning in manufacturing supply chains, ‘Risk Management’ is unaffected by causal factors, and ‘Manufacturing Processes’ is minor in adopting machine learning. The research findings aim to guide the practitioners in understanding the influence of one factor over the other and the ‘cause–effect’ relation among them. The strategies for the effective implementation of machine learning technologies may be deduced. It is a pioneering study in which novel and crucial determinants have been identified and examined in the multi-criteria environment using the DEMATEL approach.