Advertisement

Gold price forecasting research based on an improved online extreme learning machine algorithm

  • Futian Weng
  • Yinhao Chen
  • Zheng Wang
  • Muzhou HouEmail author
  • Jianshu Luo
  • Zhongchu Tian
Original Research
  • 27 Downloads

Abstract

Accurate gold price prediction is highly essential for economic and currency markets. Thus, the intelligence prediction models need to be applied to price prediction. On the basis of long-term collected daily gold, the study proposes a novel genetic algorithm regularization online extreme learning machine (GA-ROSELM), to predict gold price data which collected from public websites. Akaike Information Criterion (AIC) is introduced to build the eight input combinations of variables based on the silver price of the previous day (Silver_D1), Standard & Poor. The 500 indexes (S&P_D1), the crude oil price (Crude_D1), and the gold price of the previous 3 days (Gold_D1, Gold_D2, Gold_D3). Eight optimal variable models are established, and the final input variables are determined according to the minimum AIC value. The proposed model (GA-ROSELM) solve the problem that OS-ELM model which is easy to generate singular matrices, meanwhile, experiments demonstrate this model performs better than ARIMA, SVM, BP, ELM and OS-ELM in the gold price prediction experiment. On the test set, the root means square error of this model (GA-ROSELM) prediction compared with five other models which decreased by 13.1%, 22.4%, 53.87%, 57.84% and 37.72% respectively. In summary, the results clearly confirm the effectiveness of the GA-ROSELM model.

Keywords

Genetic algorithm AIC criterion Online learning machine Gold price forecast 

Notes

Acknowledgements

This work is supported by the National Natural Science Foundation of China (61375063, 61773404, 11301549 and 11271378), Key Program of The National Social Science Fund of China under Grants 16ATJ003. And in part by the Institute of engineering modeling and scientific computing, Central South University 2019 “Tian’an” Cup College Students’ innovation and Entrepreneurship Project.

References

  1. Akaike H (1974) A new look at statistical model identification. IEEE Trans Autom Control AC 19(6):716–723.  https://doi.org/10.1109/TAC.1974.1100705 MathSciNetCrossRefzbMATHGoogle Scholar
  2. Alexandre E, Cuadra L, Salcedosanz S (2015) Hybridizing extreme learning machines and genetic algorithms to select acoustic features in vehicle classification applications. Neurocomputing 152:58–68.  https://doi.org/10.1016/j.neucom.2014.11.019 CrossRefGoogle Scholar
  3. Baur DG, Beckmann J, Czudaj R (2016) A melting pot—gold price forecasts under model and parameter uncertainty. Int Rev Financ Anal 48:282–291.  https://doi.org/10.1016/j.irfa.2016.10.010 CrossRefGoogle Scholar
  4. Bialkowski J, Bohl MT, Stephan PM (2015) The gold price in times of crisis. Int Rev Financ Anal 41:329–339.  https://doi.org/10.1016/j.irfa.2014.07.001 CrossRefGoogle Scholar
  5. Blose LE (2010) Gold prices, cost of carry, and expected inflation. J Econ Bus 62(1):35–47.  https://doi.org/10.1016/j.jeconbus.2009.07.001 CrossRefGoogle Scholar
  6. Chandar SK (2019) Fusion model of wavelet transform and adaptive neuro fuzzy inference system for stock market prediction. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-019-01224-2 CrossRefGoogle Scholar
  7. Chen Y, Song S, Li S (2018) Domain space transfer extreme learning machine for domain adaptation. IEEE Trans Cybern 49(5):1909–1922.  https://doi.org/10.1109/TCYB.2018.2816981 CrossRefGoogle Scholar
  8. Chen S, Wang J, Zhang H (2019) A hybrid PSO-SVM model based on clustering algorithm for short-term atmospheric pollutant concentration forecasting. Technol Forecast Soc Chang 146:41–54.  https://doi.org/10.1016/j.techfore.2019.05.015 CrossRefGoogle Scholar
  9. Gao T, Li X, Chai Y (2016) Deep learning with stock indicators and two-dimensional principal component analysis for closing price prediction system. 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS). IEEE, 166–169.  https://doi.org/10.1109/ICSESS.2016.7883040
  10. Guangbin H, Qinyu Z, Cheekheong S (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501.  https://doi.org/10.1016/j.neucom.2005.12.126 CrossRefGoogle Scholar
  11. Guihao P, Nailian H, Huanzhong L (2010) Empirical analysis of gold price based on ARMA-GARCH model. Gold 31(1):5Google Scholar
  12. Hou M, Liu T, Yang Y (2017) A new hybrid constructive neural network method for impacting and its application on tungsten price prediction. Appl Intell 47(1):28–43.  https://doi.org/10.1007/s10489-016-0882-z CrossRefGoogle Scholar
  13. Huang L, Wang J (2018) Global crude oil price prediction and synchronization based accuracy evaluation using random wavelet neural network. Energy.  https://doi.org/10.1016/j.apenergy.2015.09.087 CrossRefGoogle Scholar
  14. Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892.  https://doi.org/10.1109/TNN.2006.875977 CrossRefGoogle Scholar
  15. Huang GB, Zhou H, Ding X (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42(2):513–529.  https://doi.org/10.1109/tsmcb.2011.2168604 CrossRefGoogle Scholar
  16. Huang Y, Tian K, Wu A (2019) Feature fusion methods research based on deep belief networks for speech emotion recognition under noise condition. J Ambient Intell Humaniz Comput 10(5):1787–1798.  https://doi.org/10.1007/s12652-017-0644-8 CrossRefGoogle Scholar
  17. Huynh HT, Won Y (2011) Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks. Pattern Recogn Lett 32(14):1930–1935.  https://doi.org/10.1016/j.patrec.2011.07.016 CrossRefGoogle Scholar
  18. Iosifidis A, Tefas A, Pitas I (2015) Graph embedded extreme learning machine. IEEE Trans Cybern 46(1):311–324.  https://doi.org/10.1109/TCYB.2015.2401973 CrossRefGoogle Scholar
  19. Keles D, Scelle J, Paraschiv F (2016) Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks. Appl Energy 162(162):218–230.  https://doi.org/10.1016/j.apenergy.2015.09.087 CrossRefGoogle Scholar
  20. Kim J, Moon N (2019) BiLSTM model based on multivariate time series data in multiple field for forecasting trading area. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-019-01398-9 CrossRefGoogle Scholar
  21. Kristjanpoller W, Minutolo MC (2015) Gold price volatility: a forecasting approach using the artificial neural network—GARCH model. Expert Syst Appl 42(20):7245–7251.  https://doi.org/10.1016/j.eswa.2015.04.058 CrossRefGoogle Scholar
  22. Li Y, Xie W, Li H (2017) Hyperspectral image reconstruction by deep convolutional neural network for classification. Pattern Recogn 63:371–383.  https://doi.org/10.1016/j.patcog.2016.10.019 CrossRefGoogle Scholar
  23. Mustaffa Z, Sulaiman MH, Kahar MNM (2015) Training LSSVM with GWO for price forecasting[C]. 2015 International Conference on Informatics, Electronics & Vision (ICIEV). IEEE, 1–6.  https://doi.org/10.1109/iciev.2015.7334054
  24. Nanning L, Huang GB, Saratchandran P (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423.  https://doi.org/10.1109/TNN.2006.880583 CrossRefGoogle Scholar
  25. Pan F, Zhao HB (2013) Online sequential extreme learning machine based multilayer perception with output self feedback for time series prediction. J Shanghai Jiaotong Univ 18(3):366–375.  https://doi.org/10.1007/s12204-013-1407-0 CrossRefGoogle Scholar
  26. Paroissien E (2019) Forecasting bulk prices of Bordeaux wines using leading indicators. Int J Forecast.  https://doi.org/10.1016/j.ijforecast.2019.04.021 CrossRefGoogle Scholar
  27. Salcedo-Sanz S, Camps-Valls G, Perez-Cruz F (2004) Enhancing genetic feature selection through restricted search and Walsh analysis. IEEE Trans Syst Man Cybern Part C Appl Rev 34(4):398–406.  https://doi.org/10.1109/TSMCC.2004.833301 CrossRefGoogle Scholar
  28. Shafiee S, Topal E (2010) An overview of global gold market and gold price forecasting. Resour Policy 35(3):178–189.  https://doi.org/10.1016/j.resourpol.2010.05.004 CrossRefGoogle Scholar
  29. Sivalingam KC, Mahendran S, Natarajan S (2016) Forecasting gold prices based on extreme learning machine. Int J Comput Commun Control 11(3):372.  https://doi.org/10.1002/fut.3990130605 CrossRefGoogle Scholar
  30. Stock JH, Watson MW (1988) A probability model of the coincident economic indicators. New Approach Forecast Rec.  https://doi.org/10.3386/w2772 CrossRefGoogle Scholar
  31. Wang J, Athanasopoulos G, Hyndman RJ (2018) Crude oil price forecasting based on internet concern using an extreme learning machine. Int J Forecast 34(4):665–677.  https://doi.org/10.1016/j.ijforecast.2018.03.009 CrossRefGoogle Scholar
  32. Xu J (2017) Empirical analysis of gold futures price based on ARMA model. Ind Econ Rev 4:3Google Scholar
  33. Xueying Z, Le Z, Ying S (2017) Speech emotion recognition based on decision fusion of KELM. Appl Electron Tech 8:32Google Scholar
  34. Yaseen ZM, Deo RC, Hilal A (2018) Predicting compressive strength of lightweight foamed concrete using extreme learning machine model. Adv Eng Softw 115:112–125.  https://doi.org/10.1016/j.advengsoft.2017.09.004 CrossRefGoogle Scholar
  35. Ye Y, Zhang J, Huang Z (2019) A new information fusion method of forecasting. J Ambient Intell Humaniz Comput 10(1):307–314.  https://doi.org/10.1007/s12652-017-0666-2 CrossRefGoogle Scholar
  36. Yu Y, Zhou H, Fu J (2018) Research on agricultural product price forecasting model based on improved BP neural network. J Ambient Intell Humaniz Comput.  https://doi.org/10.1007/s12652-018-1008-8 CrossRefGoogle Scholar
  37. Zhang F, Liao Z (2014) Gold price forecasting based on RBF neural network and hybrid fuzzy clustering algorithm. Lect Notes Electr Eng 241:73–84.  https://doi.org/10.1007/978-3-642-40078-06 CrossRefGoogle Scholar
  38. Zhang L, Luh PB (2005) Neural network-based market clearing price prediction and confidence interval estimation with an improved extended Kalman filter method. IEEE Trans Power Syst.  https://doi.org/10.1109/tpwrs.2004.840416 CrossRefGoogle Scholar
  39. Zhong W, Kong R, Chen G (2019) Gold prices fluctuation of co-movement forecast between China and Russia. Resour Policy 62:218–230.  https://doi.org/10.1016/j.resourpol.2019.03.012 CrossRefGoogle Scholar
  40. Zhou Z, Chen J, Zhu Z (2018) Regularization incremental extreme learning machine with random reduced kernel for regression. Neurocomputing 321:72–81.  https://doi.org/10.1016/j.neucom.2018.08.082 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  1. 1.School of Mathematics and StatisticsCentral South UniversityHu Nan ChangshaChina
  2. 2.College of ScienceNational University of Defense TechnologyHu Nan ChangshaChina
  3. 3.School of Civil EngineeringChangsha University of Science and TechnologyChangshaChina

Personalised recommendations