Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/16855
Title: Localised learning based portfolio management for stock trading using intelligent fuzzy neural approach
Authors: Mok, Luen Sheng.
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2009
Abstract: This project discussed the possibility of using artificial intelligence (AI) techniques to formulate trading decisions. It will be used to predict a stock’s closing price. It serves as an additional analyzing tool for analysts in their research and observing the trends of stocks’ movements. Genetic algorithms are becoming increasingly popular due to the fact that they are parallel and can explore multiple directions at the same time to find the optimum solution. The ability of finding a reasonably good solution in a short time has resulted in genetic algorithms to be used in making predictions. In this project, a novel hybrid intelligent system: Genetic algorithm and rough set incorporated neuro-fuzzy inference system (GARSINFIS) will be used for making the predictions. The low root mean square error (RMSE), maximum absolute percentage error (MAP) and mean absolute percentage error (MAPE) show that GARSINFIS works fairly well in the experiment. The limitation of this project is that it does not take into consideration other factors apart from the trends in the past. The recommendation and the future directions of this project will be to improvise the program to accept news feeds to affect the predicted result as well as an integrated system that can manage multiple stocks concurrently
URI: http://hdl.handle.net/10356/16855
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
MokLuenSheng09.pdf
  Restricted Access
782.48 kBAdobe PDFView/Open

Page view(s) 20

262
checked on Oct 23, 2020

Download(s) 20

21
checked on Oct 23, 2020

Google ScholarTM

Check

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