Development of specialized services for predicting the business activity indicators based on micro-service architecture

Abstract

The proposed mathematical model of specialized services for the prediction of arbitrary indicators of company activity is presented as a part of the micro-service architecture of the information system of an enterprise and provides dynamic replacement or addition of the prediction models without changing the overall algorithm of service operation. This model assigns a formal basis for the intra-component interaction of the service and makes it possible to change, add, and delete prediction services without the need for resetting the information environment of a company. The prediction model was proposed as a part of the prediction service of the company IS, based on neural network with the embedded model of moving average. This model allowed improvement of quality of predictive assessment in the case of existence of a trend in comparison with the classical neural network model due to the embedded model of moving average. The algorithm was developed for training a neural network forecasting model with the embedded moving average model, based on the inverse error spread, which allows us to tune the model to the examined time series. We considered practical aspects of using a specialized prediction service, a client application to this service, which clearly demonstrates its functionality under the mode of checking appropriateness of using a certain prediction model on a specific type of preset data.