Supply Chain Management Efficiency Improvement in the Automobile Industry Using Lean Six Sigma and Artificial Neural Network

The main aim of this article is to improve the efficiency of supply chain management in the automobile industry using two simulation software. The automotive industry like a car manufacturer always needs an accurate demand forecast to serve the uncertain demand for their products, which plays a key role in decreasing the Bullwhip effect. This article proposes an artificial-neural-network-based prediction technique with the optimization algorithm of the Levenberg–Marquardt tabu search using a questionnaire analysis. This helps to predict future demand with the best optimal solution and improves the efficiency. Product quality is the second consideration, and it plays a significant role in how customers decide whether or not to buy and repurchase a product. Alternately, to increase product quality, this article explored the supply chain using Lean Six Sigma. In addition, for assessing customer satisfaction, this article proposed the Kano 2-D quality model. Furthermore, to reduce the response time between the supplier and customer, proponents of Lean adapted just-in-time to mitigate these issues. This data analysis is performed using MATLAB and SPSS software. From the analysis of two software, the study found the best method based on their performance. In this methodology, the average risk assessment value is predicted as a high-risk factor. The convergence speed of the supply chain reaches 1.89–4.25 s in the SPSS model; furthermore, the implementation time of MATLAB is related to 16.83 s. The result shows that MATLAB can achieve the best predictive model with the proposed technique using the questionnaire data.