Operations-based classification of the bullwhip effect

Purpose Present study deals with the most discussed rather than addressed yet still an unsolved problem of supply chain known as the bullwhip effect. Operational variables affecting the bullwhip effect are identified and their role in causing the bullwhip effect has been explored using artificial neural networks. The purpose of this study is to analyze the impact of identified operational reasons that affect the bullwhip effect and to analyze the bunch of variables that are more prominent in explaining the phenomenon of the bullwhip effect. Design/methodology/approach Ten major sectors of the Indian economy are analyzed for the bullwhip effect in the present study, and the operational variables affecting the bullwhip effect in these sectors are identified. The bullwhip metric is developed as the ratio of variance in production to the variance in the demand. The impact of identified operation variables on the bullwhip effect has been discussed using the artificial neural network technique known as multilayer perceptron. The classification is also performed using neural network, logistic regression and discriminant analysis. Findings The operation variables are found to be varying with respect to sectors. The study emphasizes that analyzing the right set of operation variables with respect to the sector is required to deal with the complex problem, the bullwhip effect. The operational variables affecting the bullwhip effect are identified. The classification result of the neural network is compared with those of the logistic regression and discriminant analysis, and it is found that the dynamism present in the bullwhip effect is better classified by neural network. Research limitations/implications The study used 11 years of observations to analyze the bullwhip effect on the basis of operational variables. The bullwhip effect is a complex phenomenon, and it is explained on the basis of an extensive set of operational variables which is not exhaustive. Further, the behavioral aspect (bullwhip because of decision-making) is not explored in the present study. Practical implications The operational aspect plays a gigantic role to explain and deal with the bullwhip effect. Strategies to mitigate the bullwhip effect must be in accordance with the operational variables impacting the sector. Originality/value The study suggests a novel approach to study the bullwhip effect in supply chain management using the application of neural networks in which operational variables are taken as predictor variables.