In the paper discusses the use of big data as a tool to increase data transfer speed while providingaccess to multidimensional data in the process of forecasting product sales in the market. In this paper discussesmodern big data tools that use the MapReduce model. The big data presented in this article is a single, central-ized source of information across your entire domain. In the paper also proposes the structure of a marketinganalytics system that includes many databases in which transactions are processed in real time. For marketingforecasting of multidimensional data in Matlab, a neural network is considered and built. For training and build-ing a network, it is proposed to construct a matrix of input data for presentation in a neural network and a matrixof target data that determine the output statistical information. Input and output data in the neural network ispresented in the form of a 5x10 matrix, which represents static information about 10 products for five days ofthe week. The application of the Levenberg-Marquardt algorithm for training a neural network is considered.The results of the neural network training process in Matlab are also presented. The obtained forecasting resultsare given, which allows us to conclude about the advantages of a neural network in multivariate forecasting inreal time.