• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology

Article

An Application of AdaBoost-GRU Ensemble Model to Economic Time Series Prediction
  • VIEWS 1271
  • PDF 419

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i31.1204

Year: 2021, Volume: 14, Issue: 31, Pages: 2557-2566

Original Article

An Application of AdaBoost-GRU Ensemble Model to Economic Time Series Prediction

Ganiyu A Busari1, Nae W Kwak2, Dong H Lim3*

1PhD. Student, Department of Bio & Medical Big Data, Gyeongsang National University, 501 Jinju-daero, Jinju, 52828, Republic of Korea
2Department of Information & Statistics, Statistics, Gyeongsang National University, 501 Jinju-daero, Jinju, 52828, Republic of Korea
3Professor, Department of Information & Statistics, Department of Bio & Medical Big Data
 and RINS, Gyeongsang National University, 501 Jinju-daero, Jinju, 52828, Republic of Korea

*Corresponding Author
Email: [email protected]

Received Date:28 June 2021, Accepted Date:17 August 2021, Published Date:22 September 2021

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: Given the importance of accurate prediction of financial time series data and their benefits in the real-life, AdaBoost-GRU ensemble learning is proposed in which it’s forecasting accuracy is to be compared with AdaBoost-LSTM, single Long Short Term Memory (LSTM), and single Gated Recurrent Unit (GRU). Methods: The data for Korea Composite Stock Price Index (KOSPI) obtained from Naver Finance from January 2000 to April 2020, the Oil Price data for the entire Gyeongnam region among domestic oil price data obtained from Korea Petroleum Corporation (Opinet) and USD Exchange data provided by Naver Financial from April 2004 to May 2020 were employed. The analyses were made using mean absolute error (MAE), mean squared error (MSE) and root mean squared error (RMSE) as the performance metric. Findings: Empirical results show that the proposed method outperforms all other models that serve as benchmarked models, in all three kinds of data used in this research. This also shows that ensemble models have better performance than the single models as both AdaBoost-GRU and AdaBoost-LSTM outperform their respective single GRU and single LSTM. Novelty/Applications: This empirical study suggests that the AdaBoost-GRU ensemble-learning model is a highly promising approach for forecasting these kinds of data. However, another ensemble model that can combine AdaBoost with other single models such as ConvD1 can be developed and applied.

Keywords: Oil Price; Exchange Rate; Stock Price Index; Time Series Forecasting; AdaBoost Algorithm; Gated Recurrent Unit

References

  1. Sun S, Wei Y, Wang S. Adaboost-lstm ensemble learning for financial time series forecasting. InInternational Conference on Computational Science. 2018;p. 590–597. Available from: https://www.iccs-meeting.org/archive/iccs2018/papers/108620563.pdf
  2. Wang JH, Leu JY. Stock market trend prediction using ARIMA-based neural networks. InProceedings of International Conference on Neural Networks (ICNN'96). 1996;4:2160–2165. doi: 10.1109/ICNN.1996.549236
  4. Areekul P, Senjyu T, Toyama H, Yona A. Notice of violation of ieee publication principles: A hybrid arima and neural network model for short-term price forecasting in deregulated market. IEEE Transactions on Power Systems. 2009;25(1):524–530. doi: 10.1109/TPWRS.2009.2036488
  5. Chandar S, Kumar M, Sumathi SN, Sivanandam. Prediction of stock market price using hybrid of wavelet transform and artificial neural network. . Indian journal of Science and Technology. 2016;9:1–5. Available from: DOI:10.17485/ijst/2016/v9i8/87905
  6. Tsantekidis A, Passalis N, Tefas A, Kanniainen J. Forecasting stock prices from the limit order book using convolutional neural networks. In2017 IEEE 19th Conference on Business Informatics (CBI). 2017;1:7–12. doi: 10.1109/CBI.2017.23
  7. Ding X, Zhang Y, Liu T, Duan J. Deep learning for event-driven stock prediction. InTwenty-fourth international joint conference on artificial intelligence. 2015. Available from: http://www.wins.or.kr/DataPool/Board/4xxxx/455xx/45587/329.pdf
  8. Cho K, Merriënboer BV, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. 2014. Available from: https://arxiv.org/pdf/1406.1078.pdf
  9. Lopez-Martin, Manuel A, Sanchez-Esguevillas L, Hernandez-Callejo JI, Arribas B, Carro. Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting. Applied Sciences. 2021;11(12):5708. doi: 10.3390/app11125708
  10. Wang G, Tao T, Ma J, Li H, Fu H, Chu Y. An improved ensemble learning method for exchange rate forecasting based on complementary effect of shallow and deep features. Expert Systems with Applications. 2021;184(115569). doi: 10.1016/j.eswa.2021.115569
  11. Lopez-Martin, Manuel B, Carro A, Sanchez-Esguevillas. IoT type-of-traffic forecasting method based on gradient boosting neural networks. Future Generation Computer Systems. 2020;105:331–345. doi: 10.1016/j.future.2019.12.013
  12. Silva RGD, Ribeiro MH, Moreno SR, Mariani VC, Coelho LS. A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting. Energy. 2021;216(119174). doi: 10.1016/j.energy.2020.119174
  13. Pinto T, Praça I, Vale Z, Silva J. Ensemble learning for electricity consumption forecasting in office buildings. Neurocomputing. 2021;423:747–755. doi: 10.1016/j.neucom.2020.02.124
  15. Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences. 1997;55:119–139. Available from: https://www.sciencedirect.com/science/article/pii/S002200009791504X
  16. Schapire RE. Explaining adaboost. InEmpirical inference. (pp. 37-52) Berlin, Heidelberg. Springer. 2013.
  17. Freund Y, Schapire R, Abe N. A short introduction to boosting. Journal-Japanese Society For Artificial Intelligence. 1999;14:1612. Available from: http://www.yorku.ca/gisweb/eats4400/boost.pdf
  18. Zhang A, Lipton ZC, Li M, Smola AJ. Dive into deep learning. Unpublished Draft. 2019. Available from: https://d2l.ai/d2l-en.pdf
  20. Diao E, Ding J, Tarokh V. Restricted recurrent neural networks. In2019 IEEE International Conference on Big Data (Big Data). 2009;p. 56–63. Available from: https://arxiv.org/pdf/1908.07724
  21. Elshendy M, Colladon AF, Battistoni E, Gloor PA. Using four different online media sources to forecast the crude oil price. Journal of Information Science. 2018;44(3):408–421. Available from: https://doi.org/10.1177/0165551517698298
  22. Ahmed NK, Amir F, Atiya NE, Gayar H, El-Shishiny. An empirical comparison of machine learning models for time series forecasting. Econometric Reviews. 2010;29(5-6):594–621. Available from: https://www.tandfonline.com/doi/abs/10.1080/07474938.2010.481556
  23. Mcadam P, Mcnelis P. Forecasting inflation with thick models and neural networks. Economic Modelling. 2005;22:848–867. Available from: https://www.sciencedirect.com/science/article/pii/S026499930500043X
  24. Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks: The state of the art. . International journal of forecasting. 1998;14(1):35–62. Available from: https://www.sciencedirect.com/science/article/pii/S0169207097000447

Copyright

© 2021 Busari et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)

  • 23 September 2021

Year: 2021, Volume: 14, Issue: 31

Article Metrics


Post Graduate Fellowship in Research Communication

More articles

DON'T MISS OUT!

Subscribe now for latest articles and news.