dc.contributor.authorZhang, Jiani
dc.date.accessioned2016-05-24T06:48:10Z
dc.date.available2016-05-24T06:48:10Z
dc.date.issued2016
dc.identifier.urihttp://hdl.handle.net/10356/68136
dc.description.abstractArtificial 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.en_US
dc.format.extent74 p.en_US
dc.language.isoenen_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineeringen_US
dc.titleCommodity price prediction using neural networksen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorWang Lipo (EEE)en_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeELECTRICAL and ELECTRONIC ENGINEERINGen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record