With the development of the economy and the increasing awareness of people to invest in their own assets, stocks have become the most common way for people to manage their money. However, stocks also have strong risk and uncertainty. The emergence of artificial intelligence techniques has contributed to improving the stock forecast stability, so the stock market forecasting through artificial intelligence, in particular, the machine learning algorithms has become a popular research area. In this study, a hyper-parametric stacking-based ensemble learning model based on seasonal and trend decomposition using Loess (SEL-STL) is proposed. Firstly, the normalized preprocessing is performed on the raw data. Then, the preprocessed data is decomposed by means of seasonal and trend decomposition using Loess (STL). Subsequently, the Bayesian optimization algorithm is employed to optimize the hyper-parameters of the base prediction models. After that, the ensemble model is obtained by integrating the optimized base prediction models using the stacking-based ensemble learning method. Finally, the ensemble model is improved by further optimizing the model performance using the Adaptive Boosting. In the experiments, the datasets with three different stock exchange indices are used to evaluate the performance of the proposed model in stock price prediction. The experimental results show that the proposed model outperforms the other baseline prediction models in solving the stock price prediction problem.
| Published in | International Journal of Economics, Finance and Management Sciences (Volume 10, Issue 4) |
| DOI | 10.11648/j.ijefm.20221004.18 |
| Page(s) | 222-228 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2022. Published by Science Publishing Group |
Seasonal and Trend Decomposition, Stacking-Based Ensemble Model, Bayesian Optimization, Adaptive Boosting, Stock Price Prediction
| [1] | Chen, D. W., Zhang, J. H., and Jiang, S. X. (2020). Forecasting the short-term metro ridership with seasonal and trend decomposition using Loess and LSTM neural networks. IEEE Access, 8, 91181-91187. |
| [2] | Verrelst, J., Munoz, J., Alonso, L., Delegido, J., Rivera, J. P., Camps-Valls, G., and Moreno, J. (2012). Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3. Remote Sensing of Environment, 118, 127-139. |
| [3] | Gou, J. P., Ma, H. X., Ou, W. H., Zeng, S. N., Rao, Y. B., and Yang, H. B. (2019). A generalized mean distance-based k-nearest neighbor classifier. Expert Systems with Applications, 115, 356-372. |
| [4] | Mohammadi, B., Guan, Y. Q., Moazenzadeh, R., and Safari, M. J. S. (2021). Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation. Catena, 198, 105024. |
| [5] | Zhong, H., Wang, J. J., Jia, H. J., Mu, Y. F., and Lv, S. L. (2019). Vector field-based support vector regression for building energy consumption prediction. Applied Energy, 242, 403-414. |
| [6] | Lu, H. F., and Ma, X. (2019). Hybrid decision tree-based machine learning models for short-term water quality prediction. Chemosphere, 249, 126169. |
| [7] | Shahraki, A., Abbasi, M., and Haugen, O. (2020). Boosting algorithms for network intrusion detection: A comparative evaluation of Real AdaBoost, Gentle AdaBoost and Modest AdaBoost. Engineering Applications of Artificial Intelligence, 94, 103770. |
| [8] | Patel, J., Shah, S., Thakkar, P., and Kotecha, K. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Systems with Applications, 42, 1, 259-268. |
| [9] | Long, W., Lu, Z. C., and Cui, L. X. (2019). Deep learning-based feature engineering for stock price movement prediction. Knowledge-Based Systems, 164, 163-173. |
| [10] | Janiesch, C., Zschech, P., and Heinrich, K. (2021). Machine learning and deep learning. Electronic Markets, 31, 3, 685-695. |
| [11] | Cui, S. Z., Yin, Y. Q., Wang, D. J., Li, Z. W., and Wang, Y. Z. (2021). A stacking-based ensemble learning method for earthquake casualty prediction. Applied Soft Computing, 101, 107038. |
| [12] | Khoei, T. T., Labuhn, M. C., Caleb, T. D., Hu, W. C., and Kaabouch, N. (2021). A stacking-based ensemble learning model with Genetic Algorithm for detecting early stages of Alzheimer's disease. In 2021 IEEE International Conference on Electro/Information Technology, Mount pleasant, MI, May 14-15, pp. 215-222, 2021. |
| [13] | Wang, Y. Y., Wang, D. J., Geng, N., Wang, Y. Z., Yin, Y. Q., and Jin, Y. C. (2019). Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection. Applied Soft Computing, 77, 188-204. |
| [14] | Sameen, M. I., Pradhan, B., and Lee, S. (2020). Application of convolutional neural networks featuring Bayesian optimization for landslide susceptibility assessment. Catena, 186, 104249. |
| [15] | Letham, B., Karrer, B., Ottoni, G., and Bakshy, E. (2019). Constrained Bayesian optimization with noisy experiments. Bayesian Analysis, 14, 495-519. |
| [16] | Abbasimehr, H., and Paki, R. (2021) Prediction of COVID-19 confirmed cases combining deep learning methods and Bayesian optimization. Chaos Solitons & Fractals, 142, 110511. |
| [17] | Ghosh, I., and Datta Chaudhuri, T. (2021). FEB-stacking and FEB-DNN models for stock trend prediction: A performance analysis for pre and post Covid-19 periods. Decision Making: Applications in Management and Engineering, 4 (1), 51-84. |
| [18] | Huang, B., Ding, Q., Sun, G. Z., & Li, H. K. (2018). Stock prediction based on Bayesian-LSTM. In Proceedings of the 2018 10th International Conference on Machine Learning and Computing, February 26-28, Macau, China, pp. 128-133. |
APA Style
Chenhao Wu, Fang He. (2022). Predicting Stock Prices Using Stacking-Based Ensemble Learning and Seasonal and Trend Decomposition Using Loess. International Journal of Economics, Finance and Management Sciences, 10(4), 222-228. https://doi.org/10.11648/j.ijefm.20221004.18
ACS Style
Chenhao Wu; Fang He. Predicting Stock Prices Using Stacking-Based Ensemble Learning and Seasonal and Trend Decomposition Using Loess. Int. J. Econ. Finance Manag. Sci. 2022, 10(4), 222-228. doi: 10.11648/j.ijefm.20221004.18
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijefm.20221004.18,
author = {Chenhao Wu and Fang He},
title = {Predicting Stock Prices Using Stacking-Based Ensemble Learning and Seasonal and Trend Decomposition Using Loess},
journal = {International Journal of Economics, Finance and Management Sciences},
volume = {10},
number = {4},
pages = {222-228},
doi = {10.11648/j.ijefm.20221004.18},
url = {https://doi.org/10.11648/j.ijefm.20221004.18},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijefm.20221004.18},
abstract = {With the development of the economy and the increasing awareness of people to invest in their own assets, stocks have become the most common way for people to manage their money. However, stocks also have strong risk and uncertainty. The emergence of artificial intelligence techniques has contributed to improving the stock forecast stability, so the stock market forecasting through artificial intelligence, in particular, the machine learning algorithms has become a popular research area. In this study, a hyper-parametric stacking-based ensemble learning model based on seasonal and trend decomposition using Loess (SEL-STL) is proposed. Firstly, the normalized preprocessing is performed on the raw data. Then, the preprocessed data is decomposed by means of seasonal and trend decomposition using Loess (STL). Subsequently, the Bayesian optimization algorithm is employed to optimize the hyper-parameters of the base prediction models. After that, the ensemble model is obtained by integrating the optimized base prediction models using the stacking-based ensemble learning method. Finally, the ensemble model is improved by further optimizing the model performance using the Adaptive Boosting. In the experiments, the datasets with three different stock exchange indices are used to evaluate the performance of the proposed model in stock price prediction. The experimental results show that the proposed model outperforms the other baseline prediction models in solving the stock price prediction problem.},
year = {2022}
}
TY - JOUR T1 - Predicting Stock Prices Using Stacking-Based Ensemble Learning and Seasonal and Trend Decomposition Using Loess AU - Chenhao Wu AU - Fang He Y1 - 2022/08/17 PY - 2022 N1 - https://doi.org/10.11648/j.ijefm.20221004.18 DO - 10.11648/j.ijefm.20221004.18 T2 - International Journal of Economics, Finance and Management Sciences JF - International Journal of Economics, Finance and Management Sciences JO - International Journal of Economics, Finance and Management Sciences SP - 222 EP - 228 PB - Science Publishing Group SN - 2326-9561 UR - https://doi.org/10.11648/j.ijefm.20221004.18 AB - With the development of the economy and the increasing awareness of people to invest in their own assets, stocks have become the most common way for people to manage their money. However, stocks also have strong risk and uncertainty. The emergence of artificial intelligence techniques has contributed to improving the stock forecast stability, so the stock market forecasting through artificial intelligence, in particular, the machine learning algorithms has become a popular research area. In this study, a hyper-parametric stacking-based ensemble learning model based on seasonal and trend decomposition using Loess (SEL-STL) is proposed. Firstly, the normalized preprocessing is performed on the raw data. Then, the preprocessed data is decomposed by means of seasonal and trend decomposition using Loess (STL). Subsequently, the Bayesian optimization algorithm is employed to optimize the hyper-parameters of the base prediction models. After that, the ensemble model is obtained by integrating the optimized base prediction models using the stacking-based ensemble learning method. Finally, the ensemble model is improved by further optimizing the model performance using the Adaptive Boosting. In the experiments, the datasets with three different stock exchange indices are used to evaluate the performance of the proposed model in stock price prediction. The experimental results show that the proposed model outperforms the other baseline prediction models in solving the stock price prediction problem. VL - 10 IS - 4 ER -
Information
Email: