Stock trend behavior prediction using machine learning techniques and trading simulation.
Due to the choppy fluctuates and uncertainties in the share market, it has been a challenge for financial institution or even investors to be definite with the stock trend. The aim of the paper is to scrutinize different algorithms in data mining to identify the trend of the stock price movement. Th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/104588/1/LiauSheauChangNilamNurDorisWongHooiTen2022_StockTrendBehaviorPredictionUsingMachine.pdf http://eprints.utm.my/104588/ https://oiji.utm.my/index.php/oiji/article/view/178/131 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.utm.104588 |
|---|---|
| record_format |
eprints |
| spelling |
my.utm.1045882024-02-14T06:08:38Z http://eprints.utm.my/104588/ Stock trend behavior prediction using machine learning techniques and trading simulation. Sjarif, Nilam Nur Amir Liau, Sheau Chang Ten Wong, Doris Hooi HB Economic Theory HB615-715 Entrepreneurship. Risk and uncertainty. Property Due to the choppy fluctuates and uncertainties in the share market, it has been a challenge for financial institution or even investors to be definite with the stock trend. The aim of the paper is to scrutinize different algorithms in data mining to identify the trend of the stock price movement. This will provide contently insights to the investor to make a precise investment and grow their portfolios. Historical price movement are extracted from financial websites. Derived attributes on Simple Moving Average (SMA) with different periods are added as an input parameter. This study proposed a combination of different features to implement with machine learning algorithms which includes k-NN, SVM and J48. The study has achieved high accuracy in stock classification, with 94.872% in k-NN, 94.855% in J48 and 85.257% in SVM. This indicates that for trend movement prediction classification, SVM is the most optimal algorithm to classify the correct trend of the stock movement, followed by k-NN and J48. However, the feature selection is also crucial to have an impactful attribute as the input parameters for better and more accurate predictive analysis. Price movement forecast was also carried out to compare between linear regression, Decision Tree, LSTM and k-NN to be used for future comparison. LSTM is the best algorithm in predicting the stock price with the least RSME indicates that it rhymes closely with the actual stock price movement. Penerbit UTM Press 2022-05-22 Article PeerReviewed application/pdf en http://eprints.utm.my/104588/1/LiauSheauChangNilamNurDorisWongHooiTen2022_StockTrendBehaviorPredictionUsingMachine.pdf Sjarif, Nilam Nur Amir and Liau, Sheau Chang and Ten Wong, Doris Hooi (2022) Stock trend behavior prediction using machine learning techniques and trading simulation. Open International Journal Of Informatics, 10 (1). pp. 12-26. ISSN 2289-2370 https://oiji.utm.my/index.php/oiji/article/view/178/131 |
| institution |
Universiti Teknologi Malaysia |
| building |
UTM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Malaysia |
| content_source |
UTM Institutional Repository |
| url_provider |
http://eprints.utm.my/ |
| language |
English |
| topic |
HB Economic Theory HB615-715 Entrepreneurship. Risk and uncertainty. Property |
| spellingShingle |
HB Economic Theory HB615-715 Entrepreneurship. Risk and uncertainty. Property Sjarif, Nilam Nur Amir Liau, Sheau Chang Ten Wong, Doris Hooi Stock trend behavior prediction using machine learning techniques and trading simulation. |
| description |
Due to the choppy fluctuates and uncertainties in the share market, it has been a challenge for financial institution or even investors to be definite with the stock trend. The aim of the paper is to scrutinize different algorithms in data mining to identify the trend of the stock price movement. This will provide contently insights to the investor to make a precise investment and grow their portfolios. Historical price movement are extracted from financial websites. Derived attributes on Simple Moving Average (SMA) with different periods are added as an input parameter. This study proposed a combination of different features to implement with machine learning algorithms which includes k-NN, SVM and J48. The study has achieved high accuracy in stock classification, with 94.872% in k-NN, 94.855% in J48 and 85.257% in SVM. This indicates that for trend movement prediction classification, SVM is the most optimal algorithm to classify the correct trend of the stock movement, followed by k-NN and J48. However, the feature selection is also crucial to have an impactful attribute as the input parameters for better and more accurate predictive analysis. Price movement forecast was also carried out to compare between linear regression, Decision Tree, LSTM and k-NN to be used for future comparison. LSTM is the best algorithm in predicting the stock price with the least RSME indicates that it rhymes closely with the actual stock price movement. |
| format |
Article |
| author |
Sjarif, Nilam Nur Amir Liau, Sheau Chang Ten Wong, Doris Hooi |
| author_facet |
Sjarif, Nilam Nur Amir Liau, Sheau Chang Ten Wong, Doris Hooi |
| author_sort |
Sjarif, Nilam Nur Amir |
| title |
Stock trend behavior prediction using machine learning techniques and trading simulation. |
| title_short |
Stock trend behavior prediction using machine learning techniques and trading simulation. |
| title_full |
Stock trend behavior prediction using machine learning techniques and trading simulation. |
| title_fullStr |
Stock trend behavior prediction using machine learning techniques and trading simulation. |
| title_full_unstemmed |
Stock trend behavior prediction using machine learning techniques and trading simulation. |
| title_sort |
stock trend behavior prediction using machine learning techniques and trading simulation. |
| publisher |
Penerbit UTM Press |
| publishDate |
2022 |
| url |
http://eprints.utm.my/104588/1/LiauSheauChangNilamNurDorisWongHooiTen2022_StockTrendBehaviorPredictionUsingMachine.pdf http://eprints.utm.my/104588/ https://oiji.utm.my/index.php/oiji/article/view/178/131 |
| _version_ |
1792147845159059456 |
| score |
13.211869 |