Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/68136
Title: Commodity price prediction using neural networks
Authors: Zhang, Jiani
Keywords: DRNTU::Engineering
Issue Date: 2016
Abstract: Artificial Neural Network (ANN) which was inspired by biological information processing in human brains, has been widely applied into many fields to solve classification, clustering, signal processing and regression problems. Also, in the financial world, commodity spot price’s fluctuation can generate significant impact in economy. Interests had been arised to connect the tool: ANN with the target: commodity prices. Therefore, the objective of this project is to build, train and test ANN models for commodity price prediction. In this report, three ANN models, Back Propagation (BP), Support Vector Machine (SVM), and Radio Basis Functions (RBF) were built and trained based on different selected crude oil data sets. Three different types of datasets were selected and processed to enhance the prediction accuracy. In order to deal with the obtained raw data, implement the ANN models, and visualize the modeling results, Visual Basic Application (VBA) and MATLAB were applied. This project can be used as a reference for commodity price prediction methods in financial world, as well as an application of ANN in Artificial Intelligence field.
URI: http://hdl.handle.net/10356/68136
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Final Report.pdf
  Restricted Access
6.3 MBAdobe PDFView/Open

Page view(s)

154
Updated on May 14, 2021

Download(s) 50

31
Updated on May 14, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.