Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/52072
Title: Feature selection for stock trend prediction via support vector machine
Authors: Ng, Ivan Wei Jun.
Keywords: DRNTU::Engineering
Issue Date: 2013
Abstract: Stock market is a highly complex and non-linear dynamic system. Successful predictions in the stock market could bring in significant profits. However, prediction of the stock trend remains unresolved due to its complexity. Technical analysis is the analysis of securities by means of studying statistics generated by past market data, such as past prices and volume. These data generated were used as the input variables. Support Vector Machine is a supervised learning model, which will be used to analyze and classify data into the respective patterns identified. The aim of this project is to apply the linear Support Vector Machines strategy of feature selection to select the highest scoring feature. Once the feature set is determined, the model is used on the full training data. The resulting training model will then be used on the testing data to forecast the stock trend signal.
URI: http://hdl.handle.net/10356/52072
Schools: School of Computer Engineering 
Research Centres: Emerging Research Lab 
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 
SCE12-0236.pdf
  Restricted Access
2.82 MBAdobe PDFView/Open

Page view(s) 50

485
Updated on Nov 13, 2024

Download(s) 50

53
Updated on Nov 13, 2024

Google ScholarTM

Check

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