Feature selection for neural network based stock prediction

We propose a new methodology of feature selection for stock movement prediction. The methodology is based upon finding those features which minimize the correlation relation function. We first produce all the combination of feature and evaluate each of them by using our evaluate function. We search...

Full description

Saved in:
Bibliographic Details
Main Authors: Sugunnasil P., Somhom S.
Format: Book Series
Published: 2017
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=78650150569&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/43149
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-43149
record_format dspace
spelling th-cmuir.6653943832-431492017-09-28T06:51:06Z Feature selection for neural network based stock prediction Sugunnasil P. Somhom S. We propose a new methodology of feature selection for stock movement prediction. The methodology is based upon finding those features which minimize the correlation relation function. We first produce all the combination of feature and evaluate each of them by using our evaluate function. We search through the generated set with hill climbing approach. The self-organizing map based stock prediction model is utilized as the prediction method. We conduct the experiment on data sets of the Microsoft Corporation, General Electric Co. and Ford Motor Co. The results show that our feature selection method can improve the efficiency of the neural network based stock prediction. © 2010 Springer-Verlag. 2017-09-28T06:51:06Z 2017-09-28T06:51:06Z 2010-12-20 Book Series 18650929 2-s2.0-78650150569 10.1007/978-3-642-16699-0_15 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=78650150569&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/43149
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
description We propose a new methodology of feature selection for stock movement prediction. The methodology is based upon finding those features which minimize the correlation relation function. We first produce all the combination of feature and evaluate each of them by using our evaluate function. We search through the generated set with hill climbing approach. The self-organizing map based stock prediction model is utilized as the prediction method. We conduct the experiment on data sets of the Microsoft Corporation, General Electric Co. and Ford Motor Co. The results show that our feature selection method can improve the efficiency of the neural network based stock prediction. © 2010 Springer-Verlag.
format Book Series
author Sugunnasil P.
Somhom S.
spellingShingle Sugunnasil P.
Somhom S.
Feature selection for neural network based stock prediction
author_facet Sugunnasil P.
Somhom S.
author_sort Sugunnasil P.
title Feature selection for neural network based stock prediction
title_short Feature selection for neural network based stock prediction
title_full Feature selection for neural network based stock prediction
title_fullStr Feature selection for neural network based stock prediction
title_full_unstemmed Feature selection for neural network based stock prediction
title_sort feature selection for neural network based stock prediction
publishDate 2017
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=78650150569&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/43149
_version_ 1681422323952910336