Forecasting the Value of Iron Ore Raw Materials on the Basis of Statistical Time Series Analysis

Objective. The objective of the present article is the development of evaluation of the effectiveness of forecasting the time series of cost indicators as stochastic using known methods. Methods. The following methods and techniques of cognition were used in the research process: theoretical generalization and comparison, analysis and synthesis, induction and deduction, generalization and systematization, statistical methods of time series analysis. Results. The article presents the stages of forming a statistical analysis of a time series. It has been established that in modern conditions of evaluating the effectiveness of economic research, a more thorough analysis of the dependence of value indicators on time is necessary. Their mathematical models are usually used to describe the behavior of physical objects. If a model based on physical laws can be obtained, such a model would be deterministic. At the same time, in practice, even such a model is not completely deterministic, since a number of unaccounted factors may participate in it. For such objects, it is not possible to offer a deterministic model that allows accurate calculation of the future behavior of the object. Nevertheless, it is possible to propose a model that allows you to calculate the probability that some future value will lie in a certain interval. Such a model is called stochastic. Time series models of commodity prices in the time domain are actually stochastic. An important class of stochastic models for describing time series are stationary models. They are based on the assumption that the process remains in equilibrium with respect to a constant average level, which is confirmed by studying the time series of the cost of goods in the time domain.Mathematical models of stochastic time series were built based on the study of the real dependence of indicators on time. In practical terms, this will improve the economic performance of the enterprise. For practical implementation, a stochastic time series of the cost indicator was constructed; an economic-mathematical model for the value indicator based on a time series was formed for the purpose of forecasting. The quality of the forecast is determined not only by the forecast error, but also by the number of parameters included in the model of the forecasting function. Analysis of the data shows that the smallest forecast error occurs for the analytical trend function. Along with this, the trend function has six parameters. If we take into account the number of parameters, then the best method will be the moving average, which has an error variance of 54 with one parameter.