Determination of iron procurement strategy for manufacturing companies

Abstract

The objective of this paper is to evaluate the price development of iron (steel rebar and hot rolled coil steel) on commodity exchanges, to determine the dependence of the price of iron on prices of other major commodities (crude oil and natural gas), to forecast its future development and to propose a particular iron procurement strategy for manufacturing companies in the South Bohemian Region until the end of 2028. The content analysis method was selected to evaluate the price development. It was also used to assess the dependence of iron prices on other major commodities, which was considered using the correlation analysis method. The artificial neural network method, multilayer perceptron networks, was selected and used to forecast future price development. All calculations are performed using Statistica software (version 13). Linear regression is conducted using different functions, with 1,000 neural structures being generated each time, out of which 5 structures showing the best characteristics are selected. These are retained to forecast future prices for the 2023-2028 period in three experiments. Results are presented in tables and graphs processed in Microsoft Excel. Based on the selected variants of future steel price forecasting, a specific iron procurement strategy can be recommended for manufacturing companies in the South Bohemian Region until the end of 2028.