Big Data Analysis for Raw Material Prediction in the Industrial Sector: A Systematic Review

Noe Contreras E.D.R.; Valderrama Cassani A.; Blancas Castro Á.M.; Cornelio Ramos J.M. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2025) · DOI: 10.18687/leird2025.1.1.395

Resumen

In the context of the digital transformation of the industrial sector, this review aimed to analyze the use of Big Data in raw material prediction, with an emphasis on its application in purchase planning and inventory management. A systematic search was conducted in the Scopus database during April 2025, applying the PRISMA protocol and the PIOC strategy. Method: 829 articles were identified, of which 23 met the inclusion criteria related to the implementation of predictive techniques in manufacturing sector organizations. Results: Substantial improvements were observed in forecast accuracy, operational cost reduction, and inventory optimization, especially through the use of models such as LSTM neural networks, hybrid algorithms, and digital twins. These technologies also contributed to more informed and adaptable decision-making in contexts of high variability. Conclusions: The review provides relevant evidence on the benefits of Big Data analysis in the supply chain, although limitations are recognized due to the scarce presence of studies in Latin America and the reliance on research focused on Asia and Europe. It is recommended to conduct empirical studies in local settings in order to validate the applicability of these tools in contexts with lower digital maturity. © LEIRD 2025.All rights reserved.

Instituciones: Universidad Tecnológica del Perú