Skip to main content
SpringerLink
Log in

A novel metal futures forecasting system based on wavelet packet decomposition and stochastic deep learning model

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The forecasting technique of metals futures prices is helpful to realize the early warning for exporter and importer countries, market traders and government regulation. In order to optimize the accuracy of metal futures prices prediction, this paper establishes a novel hybrid model, which combines signal decomposition theory, stochastic theory and deep learning methods. The primary modelling process of the proposed model involves three main steps. In step I, the proposed decomposition method is employed to preprocess the raw metal futures data. The time strength weight algorithm based on the long-term memory model is trained for each subseries in step II. In step III, the final forecasting results are obtained by inverse transform after the stochastic deep learning model for each sub-series is constructed by preprocessing and training. The proposed model exhibits superior performance in metal futures forecasting by analyzing the results with multiplied practices and an original error evaluation approach called multi-scale Jensen-Shannon divergence. It can get higher forecasting accuracy than the corresponding single models and the existing hybrid models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Aye G et al (2015) Forecasting the price of gold using dynamic model averaging. Int Rev Financ Anal 41:257–266

    Article  Google Scholar 

  2. Liu C et al (2017) Forecasting copper prices by decision tree learning. Resources Policy 52:427–434

    Article  Google Scholar 

  3. Drachal K (2019) Forecasting prices of selected metals with Bayesian data-rich models. Resources Policy 64:101528

    Article  Google Scholar 

  4. Balcilar M, Hammoudeh S, Asaba NAF (2015) A regime-dependent assessment of the information transmission dynamics between oil prices, precious metal prices and exchange rates. Int Rev Econ Financ 40:72–89

    Article  Google Scholar 

  5. He K, Chen Y, Tso GKF (2017) Price forecasting in the precious metal market: A multivariate EMD denoising approach. Resources Policy 54:9–24

    Article  Google Scholar 

  6. Dooley G, Lenihan H (2005) An assessment of time series methods in metal price forecasting. Resources Policy 30(3):208–217

    Article  Google Scholar 

  7. Han X, Liu Z, Wang S (2021) An R-vine copula analysis of non-ferrous metal futures with application in Value-at-Risk forecasting. Journal of Commodity Markets, 100188

  8. Patra S (2021) Revisiting value-at-risk and expected shortfall in oil markets under structural breaks: The role of fat-tailed distributions. Energy Economics 101:105452

    Article  Google Scholar 

  9. Klein T, Todorova N (2021) Night trading with futures in China: The case of Aluminum and Copper. Resources Policy 73:102205

    Article  Google Scholar 

  10. Kriechbaumer T et al (2014) An improved wavelet-ARIMA approach for forecasting metal prices. Resources Policy 39:32–41

    Article  Google Scholar 

  11. Abdollahi H, Ebrahimi S B (2020) A new hybrid model for forecasting Brent crude oil price. Energy, 117520

  12. Sun N, Zhou J, Chen L et al (2018) An adaptive dynamic short-term wind speed forecasting model using secondary decomposition and an improved regularized extreme learning machine. Energy 165:939–957

    Article  Google Scholar 

  13. Livieris I E, Pintelas E, Pintelas P (2020) A CNN-LSTM model for gold price time-series forecasting. Neural Computing and Applications, 1–10

  14. Li J, Zhu S, Wu Q (2019) Monthly crude oil spot price forecasting using variational mode decomposition. Energy Econ 83:240–253

    Article  Google Scholar 

  15. Zendehboudi A, Baseer MA, Saidur R (2018) Application of support vector machine models for forecasting solar and wind energy resources: A review. Journal of Cleaner Production 199:272–285

    Article  Google Scholar 

  16. Wang J, Wang J (2015) Forecasting stock market indexes using principle component analysis and stochastic time effective neural networks. Neurocomputing 156:68–78

    Article  Google Scholar 

  17. Wang J, Wang J (2016) Forecasting energy market indices with recurrent neural networks: Case study of crude oil price fluctuations. Energy 102:365–374

    Article  Google Scholar 

  18. Wang B, Wang J (2020) Deep multi-hybrid forecasting system with random EWT extraction and variational learning rate algorithm for crude oil futures. Expert Systems with Applications, 113686

  19. Su H, Zio E, Zhang J et al (2019) A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced Deep-RNN model. Energy 178:585–597

    Article  Google Scholar 

  20. Seyedzadeh S, Rahimian FP, Rastogi P et al (2019) Tuning machine learning models for prediction of building energy loads. Sustainable Cities and Society 47:101484

    Article  Google Scholar 

  21. Tavassoli-Hojati Z, Ghaderi SF, Iranmanesh H et al (2020) A self-partitioning local neuro fuzzy model for short-term load forecasting in smart grids. Energy 199:117514

    Article  Google Scholar 

  22. Berradi Z, Lazaar M (2019) Integration of principal component analysis and recurrent neural network to forecast the stock price of Casablanca stock exchange. Procedia Comput Sci 148:55–61

    Article  Google Scholar 

  23. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  24. Yu X, Feng W, Wang H et al (2020) An attention mechanism and multi-granularity-based Bi-LSTM model for Chinese Q&A system. Soft Comput 24(8):5831–5845

    Article  Google Scholar 

  25. Liu G, Guo J (2019) Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing 337:325–338

    Article  Google Scholar 

  26. Sagheer A, Kotb M (2019) Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323:203–213

    Article  Google Scholar 

  27. Hussain T, Muhammad K, Ullah A et al (2019) Cloud-assisted multiview video summarization using CNN and bidirectional LSTM. IEEE Transactions on Industrial Informatics 16(1):77–86

    Article  Google Scholar 

  28. Kim HY, Won CH (2018) Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications 103:25–37

    Article  Google Scholar 

  29. Jun W, Lingyu T, Yuyan L et al (2017) A weighted EMD-based prediction model based on TOPSIS and feed forward neural network for noised time series. Knowledge-Based Systems 132:167–178

    Article  Google Scholar 

  30. Safari A, Davallou M (2018) Oil price forecasting using a hybrid model. Energy 148:49–58

    Article  Google Scholar 

  31. Chen S, Ren M, Sun W (2021) Combining two-stage decomposition based machine learning methods for annual runoff forecasting. Journal of Hydrology 603:126945

    Article  Google Scholar 

  32. Peng S, Chen R, Yu B et al (2021) Daily natural gas load forecasting based on the com- bination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm. J Natural Gas Sci Eng 95:104175

    Article  Google Scholar 

  33. Liu H, Yu C, Wu H, et al (2020) A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting. Energy, 117794

  34. Yang W, Wang J, Niu T et al (2019) A hybrid forecasting system based on a dual decomposition strategy and multi-objective optimization for electricity price forecasting. Appl Energy 235:1205–1225

    Article  Google Scholar 

  35. Wang J, Wang J (2017) Forecasting stochastic neural network based on financial empirical mode decomposition. Neural Networks 90:8–20

    Article  Google Scholar 

  36. Wang D, Luo H, Grunder O et al (2017) Multi-step ahead electricity price forecasting using a hybrid model based on two-layer decomposition technique and BP neural network optimized by firefly algorithm. Appl Energy 190:390–407

    Article  Google Scholar 

  37. Duan J, Zuo H, Bai Y et al (2021) Short-term wind speed forecasting using recurrent neural networks with error correction. Energy 217:119397

    Article  Google Scholar 

  38. Abdoos AA (2016) A new intelligent method based on combination of VMD and ELM for short term wind power forecasting. Neurocomputing 203:111–120

    Article  Google Scholar 

  39. Liu H, Chen C (2019) Data processing strategies in wind energy forecasting models and applications: a comprehensive review. Appl Energy 249:392–408

    Article  Google Scholar 

  40. Niu H, Xu K, Wang W (2020) A hybrid stock price index forecasting model based on variational mode decomposition and LSTM network. Applied Intelligence, 1–14

  41. Jallal MA, Gonzalez-Vidal A, Skarmeta AF et al (2020) A hybrid neuro-fuzzy inference system-based algorithm for time series forecasting applied to energy consumption prediction. Applied Energy 268:114977

    Article  Google Scholar 

  42. Lin H, Sun Q, Chen SQ (2020) Reducing exchange rate risks in international trade: A hybrid forecasting approach of CEEMDAN and multi-layer LSTM. Sustainability 12(6):2451

    Article  Google Scholar 

  43. da Silva RG, Ribeiro MHDM, Moreno SR et al (2021) A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting. Energy 216:119174

    Article  Google Scholar 

  44. Moreno SR, da Silva RG, Mariani VC et al (2020) Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network. Energy Conversion and Management 213:112869

    Article  Google Scholar 

  45. Yang Y, Wang J (2021) Forecasting wavelet neural hybrid network with financial ensemble empirical mode decomposition and MCID evaluation. Expert Systems with Applications 166:114097

    Article  Google Scholar 

  46. Menéndez ML, Pardo JA, Pardo L et al (1997) The jensen-shannon divergence. Journal of the Franklin Institute 334(2):307–318

    Article  MathSciNet  MATH  Google Scholar 

  47. Joshi R, Kumar S (2019) A dissimilarity measure based on Jensen Shannon divergence measure. International Journal of General Systems 48(3):280–301

    Article  MathSciNet  Google Scholar 

  48. Coifman R R, Meyer Y, Wickerhauser V (1992) Wavelet analysis and signal processing. In Wavelets and their applications. Sudbury, MA: Jones and Barlett, 153–178

  49. El-Hendawi M, Wang Z (2020) An ensemble method of full wavelet packet transform and neural network for short term electrical load forecasting. Electric Power Systems Research 182:106265

    Article  Google Scholar 

  50. Tayab UB, Zia A, Yang F et al (2020) Short-term load forecasting for microgrid energy management system using hybrid HHO-FNN model with best-basis stationary wavelet packet transform. Energy 203:117857

    Article  Google Scholar 

  51. Liu H, Mi X, Li Y (2018) Comparison of two new intelligent wind speed forecasting approaches based on wavelet packet decomposition, complete ensemble empirical mode decomposition with adaptive noise and artificial neural networks. Energy Conversion and Management 155:188–200

    Article  Google Scholar 

  52. Amjady N, Keynia F (2009) Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm. Energy 34(1):46–57

    Article  Google Scholar 

  53. Liu H, Mi X, Li Y (2018) Smart deep learning based wind speed prediction model using wavelet packet decomposition, convolutional neural network and convolutional long short term memory network. Energy Conversion and Management 166:120–131

    Article  Google Scholar 

  54. Schmidhuber J, Hochreiter S, Bengio Y (2001) Evaluating benchmark problems by random guessing. A Field Guide to Dynamical Recurrent Networks, ed. J. Kolen and S. Cremer, 231–235

  55. Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. European J Oper Res 270(2):654–669

    Article  MathSciNet  MATH  Google Scholar 

  56. Han L, Jing H, Zhang R et al (2019) Wind power forecast based on improved Long Short Term Memory network. Energy 189:116300

    Article  Google Scholar 

  57. He F, Zhou J, Feng Z et al (2019) A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm. Appl Energy 237:103–116

    Article  Google Scholar 

  58. Dufresne D (2001) The integral of geometric brownian motion. Adv Appl Probab 33:223–241

    Article  MathSciNet  MATH  Google Scholar 

  59. Gatheral J, Schied A (2011) Optimal trade execution under geometric Brownian motion in the almgren and chriss framework. International Journal of Theoretical & Applied Finance 14:353–368

    Article  MathSciNet  MATH  Google Scholar 

  60. Dudek G (2019) Generating random weights and biases in feedforward neural networks with random hidden nodes. Inform Sci 481:33–56

    Article  MathSciNet  Google Scholar 

  61. Abdechiri M, Meybodi MR, Bahrami H (2013) Gases Brownian motion optimization: an algorithm for optimization(GBMO). Appl Soft Comput 13(5):2932–2946

    Article  Google Scholar 

  62. Yang Y, Wang J, Wang B (2020) Prediction model of energy market by long short term memory with random system and complexity evaluation. Appl Soft Comput 95:106579

    Article  Google Scholar 

  63. Abiyev RH (2011) Fuzzy wavelet neural network based on fuzzy clustering and gradient techniques for time series prediction. Neural Computing and Applications 20:249–259

    Article  Google Scholar 

  64. Makridakis S (1993) Accuracy measures: theoretical and practical concerns. International Journal of Forecasting 9:527–529

    Article  Google Scholar 

  65. Liu XT (2010) Study on data normalization in bp neural network. Mechanical Engineering & Automation 3:122–123

    Google Scholar 

  66. Plawiak P, Abdar M, Acharya UR (2019) Application of new deep genetic cascade ensemble of SVM classifiers to predict the Australian credit scoring. Appl Soft Comput 84:105740

    Article  Google Scholar 

  67. Wang H, Gu J, Wang S (2017) An effective intrusion detection framework based on SVM with feature augmentation. Knowledge-Based Systems 136:130–139

    Article  Google Scholar 

  68. Papadimitriou T, Gogas P, Stathakis E (2014) Forecasting energy markets using support vector machines. Energy Economics 44:135–142

    Article  Google Scholar 

  69. Costa M, Goldberger AL, Peng CK (2005) Multiscale entropy analysis of biological signals. Phys Rev E 71:021906

    Article  MathSciNet  Google Scholar 

  70. Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30

    MathSciNet  MATH  Google Scholar 

  71. Fawaz HI, Forestier G, Weber J et al (2019) Deep learning for time series classification: a review. Data Mining and Knowledge Discovery 33(4):917–963

    Article  MathSciNet  MATH  Google Scholar 

  72. Ribeiro GT, Santos AAP, Mariani VC et al (2021) Novel hybrid model based on echo state neural network applied to the prediction of stock price return volatility. Expert Systems with Applications 184:115490

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the financial supports from the funds of North China University of Technology, PR China (Grant No.110051360002), National Natural Science Foundation of China (Grant No.61903006) and the Fundamental Research Funds for the Universities in Beijing (Grant No.110052972027/007).

Author information

Authors and Affiliations

  1. Department of Statistics, College of Science, North China University of Technology, 100144, Beijing, People’s Republic of China

    Jie Wang

Authors
  1. Jie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jie Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, J. A novel metal futures forecasting system based on wavelet packet decomposition and stochastic deep learning model. Appl Intell 52, 9334–9352 (2022). https://doi.org/10.1007/s10489-021-03083-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-03083-x

Keywords

Search

Navigation