<![CDATA[Objective: Geopolitical uncertainty, supply chain disruptions, and dynamic market conditions underscore the critical role of demand forecasting in modern business strategy. The results of accurate demand forecasting enable organizations to anticipate customer demand, perform optimal inventory management, improve supply chain efficiency, and make strategic decisions based on data. Forecasting models have currently experienced quite rapid development along with the integration of technologies such as machine learning and deep learning, which are able to overcome the limitations of traditional forecasting models in processing complex and nonlinear data. Integration of technology into demand forecasting models has been proven to improve the accuracy and adaptability of forecasting models, but there are still challenges in its implementation related to data quality, selection of appropriate forecasting models, and availability of computing resources. The purpose of this study is to identify research trends, literature gaps, and global collaborations in demand forecasting model development and to formulate a comprehensive framework to optimize demand forecasting implementation. Method: This study uses a mixed method by conducting bibliometric analysis on 502 documents and content analysis on 144 relevant documents from the Scopus database. Results: The results of this study indicate an increasing trend in the use of hybrid forecasting models that combine traditional forecasting models with machine learning or deep learning. Novelty: This study also proposes a comprehensive framework that can be used to optimize the implementation of demand forecasting with the aim of improving forecast accuracy and strengthening the organization's ability to anticipate a dynamic and uncertain global market environment.]]>
Copyrights © 2026
