Understanding the Applicability of Big Data Analytics to Improve Demand Forecasting in the Supply Chain in Automotive Industries

Big Data analytics are now being used more and more in studies to estimate demand in the automobile sector. However, it was observed that supply chain demand forecasting has not been widely used in practice. Additionally, a few significant gaps were discovered, such as the lack of studies focusing on using product-in-use data for demand forecasting for multiple items in the automotive industry and the challenges and risks associated with using big data analytics in supply chain management, such as data sharing, a lack of trained personnel, and security issues. This dissertation uses Big Data Analytics (BDA) in a business simulation game to examine the significance of demand forecasting in the automotive industry. Innovative tactics are necessary to maintain competitiveness in the automobile industry due to its complexity, fuelled by globalization and technological improvements. The study starts by evaluating earlier relevant material. After that, it examines group dynamics, decision-making, and strategic outcomes, and then it examines market share, gross margin percentage, and financial indicators from the business game "executive." The effectiveness of demand forecasting is then illustrated with a case study involving the car model MacNZ. This study emphasizes the importance of analytics in monitoring performance and assisting in decision-making despite the drawbacks of simulated environments. While acknowledging the difficulties brought on by the intricacies of the actual world, the study highlights the promise of demand forecasting in optimizing consumer satisfaction and profitability. This paper emphasizes how crucial it is to close the gap between simulations and reality to utilize the advantages of analytics in automotive demand forecasting effectively.

Published by: ResearchGate

View my publication

Sep 11, 2023