Analysis of demand in steel and iron industry – latent variables model

• Authors: Barska, Magdalena

Abstracts

EN

Demand in the steel and iron industry is influenced by multiple factors. Not all of them can be identified and measured. The paper presents the results of the analysis of the levels of demand achieved by a selected enterprise from this sector in the years 2010–2014. The aim of the study is to build a hidden Markov model which would reflect the turning points of this demand, thus making it possible to forecast its future levels. The model’s forecasting properties and stability have been examined. A simulation has been carried out that involved generating a high number of series for selected model parameters and checking their properties. This demonstrated that a three-state second order hidden Markov model was most relevant to the purpose of the study. Thanks to the model’s application, it was possible to describe states which could potentially shape the demand. Moreover, taking the transition state into consideration allowed spotting the signal about the upcoming replacement of the growth phase with the decline phase, and vice versa. The presented second order hidden Markov model can serve as an alternative to the traditional methods of the analysis of time series. The forecast generated by the model informs about the shaping of a trend in demand and serves as an indication of the shifts in economic cycles.

Keywords

EN

forecasting; demand; latent variables; hidden Markov models

• Publisher: Główny Urząd Statystyczny
• Journal: Przegląd Statystyczny
• Year: 2019
• Volume: 66
• Issue: 4
• Pages: 247-269

Dates

published

2020-05-11

Contributors

author

Barska, Magdalena

Identifiers

DOI

10.5604/01.3001.0014.0951