A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)
The prediction of stock prices has become an exciting area for researchers as well as academicians due to its economic impact and potential business profits. This study proposes a novel multiclass classification ensemble learning approach for predicting stock prices based on historical data using fe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sulaimani Polytechnic University
2020-04-01
|
| Series: | Kurdistan Journal of Applied Research |
| Subjects: | |
| Online Access: | https://www.kjar.spu.edu.iq/index.php/kjar/article/view/427 |
| _version_ | 1797193738020192256 |
|---|---|
| author | Rebwar M. Nabi Soran Ab. M. Saeed Habibollah Harron |
| author_facet | Rebwar M. Nabi Soran Ab. M. Saeed Habibollah Harron |
| author_sort | Rebwar M. Nabi |
| collection | DOAJ |
| description | The prediction of stock prices has become an exciting area for researchers as well as academicians due to its economic impact and potential business profits. This study proposes a novel multiclass classification ensemble learning approach for predicting stock prices based on historical data using feature engineering. The proposed approach comprises four main steps, which are pre-processing, feature selection, feature engineering, and ensemble methods. We use 11 datasets from Nasdaq and S&P 500 to ensure the accuracy of the proposed approach. Furthermore, eight feature selection algorithms are studied and implemented. More importantly, a feature engineering concept is applied to construct two new features, which are appears to be very auspicious in terms of improving classification accuracy, and this is considered the first study to use feature engineering for multiclass classification using ensemble methods. Finally, seven ensemble machine learning (ML) algorithms are used and compared to discover the ultimate collaboration prediction model. Besides, the best feature selection algorithm is proposed. This study proposes a novel multiclass classification approach called Gradient Boosting Machine with Feature Engineering (GBM-wFE) and Principal Component Analysis (PCA) as the feature selection. We find that GBM-wFE outperforms the previous studies and the overall prediction results are auspicious, as MAPE of 0.0406% is achieved, which is considered the best result compared to the available studies in the literature.
|
| first_indexed | 2024-03-07T15:27:05Z |
| format | Article |
| id | doaj.art-c0ee5e34a0c543e3a75dd61e9e0ac16b |
| institution | Directory Open Access Journal |
| issn | 2411-7684 2411-7706 |
| language | English |
| last_indexed | 2024-04-24T05:45:09Z |
| publishDate | 2020-04-01 |
| publisher | Sulaimani Polytechnic University |
| record_format | Article |
| series | Kurdistan Journal of Applied Research |
| spelling | doaj.art-c0ee5e34a0c543e3a75dd61e9e0ac16b2024-04-23T17:20:52ZengSulaimani Polytechnic UniversityKurdistan Journal of Applied Research2411-76842411-77062020-04-015110.24017/science.2020.1.3427A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE)Rebwar M. Nabi0Soran Ab. M. Saeed1Habibollah Harron2Technical College of Informatics, Sulaimani Polytechnic University, Sulaimani, IraqVP for Scientific Affairs, Sulaimani Polytechnic University, Sulaimani, IraqUniversity of Technology Malaysia, Johor, MalaysiaThe prediction of stock prices has become an exciting area for researchers as well as academicians due to its economic impact and potential business profits. This study proposes a novel multiclass classification ensemble learning approach for predicting stock prices based on historical data using feature engineering. The proposed approach comprises four main steps, which are pre-processing, feature selection, feature engineering, and ensemble methods. We use 11 datasets from Nasdaq and S&P 500 to ensure the accuracy of the proposed approach. Furthermore, eight feature selection algorithms are studied and implemented. More importantly, a feature engineering concept is applied to construct two new features, which are appears to be very auspicious in terms of improving classification accuracy, and this is considered the first study to use feature engineering for multiclass classification using ensemble methods. Finally, seven ensemble machine learning (ML) algorithms are used and compared to discover the ultimate collaboration prediction model. Besides, the best feature selection algorithm is proposed. This study proposes a novel multiclass classification approach called Gradient Boosting Machine with Feature Engineering (GBM-wFE) and Principal Component Analysis (PCA) as the feature selection. We find that GBM-wFE outperforms the previous studies and the overall prediction results are auspicious, as MAPE of 0.0406% is achieved, which is considered the best result compared to the available studies in the literature. https://www.kjar.spu.edu.iq/index.php/kjar/article/view/427Stock Market Forecasting, Feature Engineering Feature Selection Machine Learning Predictive Analysis Predictable Movement Multiclass Classification |
| spellingShingle | Rebwar M. Nabi Soran Ab. M. Saeed Habibollah Harron A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) Kurdistan Journal of Applied Research Stock Market Forecasting, Feature Engineering Feature Selection Machine Learning Predictive Analysis Predictable Movement Multiclass Classification |
| title | A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) |
| title_full | A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) |
| title_fullStr | A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) |
| title_full_unstemmed | A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) |
| title_short | A Novel Approach for Stock Price Prediction Using Gradient Boosting Machine with Feature Engineering (GBM-wFE) |
| title_sort | novel approach for stock price prediction using gradient boosting machine with feature engineering gbm wfe |
| topic | Stock Market Forecasting, Feature Engineering Feature Selection Machine Learning Predictive Analysis Predictable Movement Multiclass Classification |
| url | https://www.kjar.spu.edu.iq/index.php/kjar/article/view/427 |
| work_keys_str_mv | AT rebwarmnabi anovelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe AT soranabmsaeed anovelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe AT habibollahharron anovelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe AT rebwarmnabi novelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe AT soranabmsaeed novelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe AT habibollahharron novelapproachforstockpricepredictionusinggradientboostingmachinewithfeatureengineeringgbmwfe |