Deep Index Price Forecasting in Steel Industry
Thittaporn Ganokratanaa, Mahasak Ketcham
Abstract
Steel is one of the most expensive materials in the construction industry. Currently, Thailand imports steel from abroad, facing a price fluctuation due to the economy, production capacity, and consumption in domestic and international markets. The cost control of the steel price can also be unstable and risky to purchase. To handle these issues, there is a need for good management of the quantity and procurement of steel at the right price. Thus, we propose a prediction of the steel price index in construction using deep learning neuron networks. Our experimental results show good performance as our mean square error equals 2.34. Our proposed method can be applied for decision-making support and used as a reliable system for steel purchases in construction projects.