Big data analytics (BDA) in supply chain management (SCM) is receiving a growing attention. This is due to the fact that BDA has a wide range of applications in SCM, including customer behavior analysis, trend analysis, and demand prediction. In this survey, we investigate the predictive BDA applications in supply chain demand forecasting to propose a classification of these applications, identify the gaps, and provide insights for future research. We classify these algorithms and their applications in supply chain management into time-series forecasting, clustering, K-nearest-neighbors, neural networks, regression analysis, support vector machines, and support vector regression. This survey also points to the fact that the literature is particularly lacking on the applications of BDA for demand forecasting in the case of closed-loop supply chains (CLSCs) and accordingly highlights avenues for future research.
Forecasting demand plays a major role in manufacturing and a great big influence in modern countries. A good forecast can save the cost, lack of demand and expenses of surplus. Existing of oil in the production chain in various manufactures shows its importance. Main Object of this paper is to forecast Iran oil consumption forecasting, by using Support Vector Regression algorithm, which is measured to determine the amount of its extraction to be sell based on market's demands. Predicting the amount of oil extraction is correlated with some other important deliberations in that country. For such diversity, the utilized algorithm employs a neural network to estimate a function between social and economic inputs and oil consumption as output. GDP, population, import and export are the inputs and the vital considered parameters of this study. The required data regarding to the oil production and extraction is taken from OPEC bulletin. To accurately reach to our main aim, we used the data from 1987 to 2011, which the available data from 1987 to 2006 is used to train the algorithm and data from 2007 to 2011 for tests the capability. The results show the algorithm has 0.0005 errors for the last five years and the SVR algorithm can be more accurate than other development approaches in oil consumption forecasting and shows the aim significance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.