Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChandra Limantara.-
dc.description.abstractPredicting market behavior towards the attainment of profit maximization in financial stock trading poses a tremendous challenge since the traders’ behavior is dynamic, complex and unpredictable due to involvement of emotions, human preferences and multiple learning capabilities. Although the previously developed methods, like price prediction using neural-based architecture or market sentiment prediction using historical data, have been useful to tackle specific problems in the financial domain, they still could not fit the entire picture, i.e. a general model that can model human cognitive behavior in the financial domain. This project aims to build a novel cognitive model using Soar general cognitive architecture that could model human behavior in financial-trading system. Ultimately, the agent shall not demonstrate certain capabilities independently, but integrate different aspects of human cognitive behavior in financial trading. As the first attempt to model human behavior in financial-trading, this project focuses on formulating the basic Soar model for financial domain and enhancing its performance by incorporating reinforcement learning capability on top of the pure symbolic encoded processing. Finally, it will investigate the synergy of the reinforcement learning component with the basic model by examining the performance of the model in real time stock trading.en_US
dc.format.extent104 p.en_US
dc.subjectDRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligenceen_US
dc.titleFinancial trading system modeling in Soar cognitive architectureen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorQuek Hiok Chaien_US
dc.contributor.schoolSchool of Computer Engineeringen_US
dc.description.degreeBachelor of Engineering (Computer Science)en_US
dc.contributor.researchCentre for Computational Intelligenceen_US
item.fulltextWith Fulltext-
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
  Restricted Access
5.87 MBAdobe PDFView/Open

Page view(s) 50

Updated on Dec 4, 2020


Updated on Dec 4, 2020

Google ScholarTM


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