Information system for forecasting sales of the range of building materials on the online trading platform based on the neural network tensor flow

Abstract

This work is devoted to creating a system for forecasting sales of building materials numbers on the online trading platform based on the neural network Tensor flow. It was decided to develop an information-analytical system by building a tree of goals and analysing the hierarchy. The system is created as an application that runs in a web browser. The application will be available to everyone with the ability to add restrictions later. Sales forecasting is done by obtaining data from various APIs and working with ready-made data sets, allowing you to forecast the future product offer dates. To get a sales forecast, you need to enter data, train the model, validate our finished model and make a forecast.