Estimation of Iron Ore Price in reference to Major Economic Indices using Artificial Neural Network
Access Status
Open access
Date
2024Supervisor
Apurna Ghosh
Erkan Topal
Type
Thesis
Award
MPhil
Metadata
Show full item recordFaculty
Science and Engineering
School
WASM: Minerals, Energy and Chemical Engineering
Collection
Abstract
Iron ore is an essential commodity in human civilization where research its prediction method was limited to date. The Granger causality test and VECM proved that there is a bi-directional influence between the iron ore price and the oil, copper, and Australian coal prices. Linear Levenberg-Marquardt method predicted with highest accuracy of 5.92% difference between prediction and actual for 1 month ahead, 9.48% for 2 months ahead, and 11.21% for 3 months ahead respectively.