Method for Predicting Raw Material Prices for Product Production over Long Periods

Abstract

A construction company may invest capital and participate in a special purpose company (SPC) for financing a plant project if high profitability is expected from product production after completion. Thus, the construction company should decide whether to invest on the basis of production costs as well as construction costs. The impact of production costs on profitability is especially large, because products are produced over a long period. This study proposes a method for predicting raw material prices with the aim of contributing to more accurate predictions of profitability. The prediction method is a multivariate time series analysis and the prediction target in this study is the price of iron ore, which is the largest contributor to the price of raw materials for steel products. Following established practices and previous studies, the accuracy of the prediction results was compared with past average values over a specified period. The proposed method was found to be more than 2.3 times more accurate than past average values. The proposed method was applied to predicting the price of iron ore in this study, but for the improvement of prediction accuracy the method may apply to other raw material prices that do not use a statistical method for prediction.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 28 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.