A monetary policy prediction model based on deep learning

  • Minrong LuEmail author
Advances in Parallel and Distributed Computing for Neural Computing


Applying neural network and error t-value test, this study trains and analyzes 28 interest rate changes of China’s macro-monetary policy and the mutual influences between reserve adjustments and financial markets for 51 times from 2000 to 2018 according to the data correlation between financial market and monetary policy. Through the principal component analysis, the bilateral financial risk system and data set are established, and the data set pre-process and dimensionality reduction are carried out to extract the most informative features. Six training cases are designed with processed features, and then the cases are input to each neural network model for combined prediction. Firstly, based on backpropagation neural network (BP), the forecasting model of monetary policy is established. Then, considering the importance characteristics of financial index data, expert weights based on BP, are introduced to propose weights backpropagation (WBP) model. On the basis of the timing characteristics of financial market, the WBP model is improved and the timing weights backpropagation (TWBP) model is proposed. Experiments show that different training cases bring out various effects. The accuracy rate of interest rate and reserve change value is lower than the original value after training. The mutation after data processing affects the learning of neural network. At the same time, the WBP and TWBP models improve according to the importance and timing characteristics of financial indicators have less errors in results, and the TWBP model has higher accuracy. When the number of hidden layers is 3, good results can be obtained, but in manifold training of the timing cycle, the efficiency of that is not as good as the WBP model.


Neural network Time series Monetary policy Financial risks 



This work was supported social science research base of finance and accounting research center of Fujian province, in part by asset evaluation research project of Fujian social science planning and research base under Grant JXY201801-08 and JXY201801-05, in part by the “Internet+” virtual simulation experimental teaching platform for the key project of the young and middle-aged teachers in Fujian province under Grant JZ180190, in part by the active project reporting mode under the background of cloud network in the major project of Fujian province social science base in 2018 Research under Grant FJ2018JDZ014, in part by the project of Fujian institute of technology under Grant GB-RJ-17-58.

Compliance with ethical standards

Conflict of interest

The author Minrong Lu is from Fujian Jiangxia University, and he declares that he has no conflict of interest.


  1. 1.
    Black SE, Devereux PJ, Lundborg P (2017) On the origins of risk-taking in financial markets. J Financ 72(5):100–105CrossRefGoogle Scholar
  2. 2.
    Riccioni J, Cerqueti R (2018) Regular paths in financial markets: investigating the Benford’s law. Chaos Solitons Fractals 107:186–194MathSciNetCrossRefGoogle Scholar
  3. 3.
    Lin EMH, Sun EW, Yu MT (2018) Systemic risk, financial markets, and performance of financial institutions. Ann Oper Res 262(2):579–603MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Lengnick M, Wohltmann HW (2016) Optimal monetary policy in a new Keynesian model with animal spirits and financial markets. J Econ Dyn Control 64:148–165MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Dafermos Y, Nikolaidi M, Galanis G (2018) Climate change, financial stability and monetary policy. Ecol Econ 152:219–234CrossRefGoogle Scholar
  6. 6.
    Platen E, Rebolledo R (1996) Principles for modelling financial markets. J Appl Probab 33(3):601–613MathSciNetzbMATHCrossRefGoogle Scholar
  7. 7.
    Li Kenli, Tang Xiaoyong, Li Keqin (2014) Energy-efficient stochastic task scheduling on heterogeneous computing systems. IEEE Trans Parallel Distrib Syst 25(11):2867–2876CrossRefGoogle Scholar
  8. 8.
    Antipov A, Meade N (2002) Forecasting call frequency at a financial services call centre. J Oper Res Soc 53(9):953–960zbMATHCrossRefGoogle Scholar
  9. 9.
    Li C, Chiang TW (2013) Complex neurofuzzy ARIMA forecasting–a new approach using complex fuzzy sets. IEEE Trans Fuzzy Syst 21(3):567–584CrossRefGoogle Scholar
  10. 10.
    Kayalar DE, Küçüközmen CC, Selcuk-Kestel AS (2017) The impact of crude oil prices on financial market indicators: copula approach. Energy Econ 61:162–173CrossRefGoogle Scholar
  11. 11.
    Yuming Xu, Li Kenli, Jingtong Hu, Li Keqin (2014) A genetic algorithm for task scheduling on heterogeneous computing systems using multiple priority queues. Inf Sci 270:255–287MathSciNetzbMATHCrossRefGoogle Scholar
  12. 12.
    Ganda F (2019) The environmental impacts of financial development in OECD countries: a panel GMM approach. Environ Sci Pollut Res 5:11–15Google Scholar
  13. 13.
    Jian ZH, Zhu BS, Shuang LI (2012) Dynamic inflation target, money supply mechanism and China’s economic fluctuation: A DSGE-based analysis. Chin J Manag SciGoogle Scholar
  14. 14.
    Yuming Xu, Li Kenli, He Ligang, Zhang Longxin, Li Keqin (2015) A hybrid chemical reaction optimization scheme for task scheduling on heterogeneous computing systems. IEEE Trans Parallel Distrib Syst 26(12):3208–3222CrossRefGoogle Scholar
  15. 15.
    Chen J, Li K, Bilal K, Metwally AA, Li K, Yu PS (2018) Parallel protein community detection in large-scale ppi networks based on multi-source learning. IEEE/ACM Trans Comput Biol Bioinf.
  16. 16.
    Chen C, Tiao GC (1990) Random level-shift time series models, arima approximations, and level-shift detection. J Bus Econ Stat 8(1):83–97Google Scholar
  17. 17.
    Einav L, Levin J (2014) Economics in the age of big data. Science 346(6210):124–130CrossRefGoogle Scholar
  18. 18.
    Zhang XPS, Wang F (2017) Signal processing for finance, economics, and marketing: concepts, framework, and big data applications. IEEE Signal Process Mag 34(3):14–35CrossRefGoogle Scholar
  19. 19.
    Araújo RDA (2012) A morphological perceptron with gradient-based learning for Brazilian stock market forecasting. Neural Netw 28:61–81CrossRefGoogle Scholar
  20. 20.
    Chung H, Shin KS (2010) Genetic algorithm-optimized long short-term memory network for stock market prediction. Sustainability 10:3765CrossRefGoogle Scholar
  21. 21.
    Li Kenli, Yang Wangdong, Li Keqin (2015) Performance analysis and optimization for SPMV on GPU using probabilistic modeling. IEEE Trans Parallel Distrib Syst 26(1):196–205MathSciNetCrossRefGoogle Scholar
  22. 22.
    Chen Jianguo, Li Kenli, Tang Zhuo, Yu Shui, Li Keqin (2017) A parallel random forest algorithm for big data in spark cloud computing environment. IEEE Trans Parallel Distrib Syst 28(4):919–933CrossRefGoogle Scholar
  23. 23.
    Lazer D, Kennedy R, King G (2014) Big data. the parable of Google Flu: traps in big data analysis. Science 343(6176):1203CrossRefGoogle Scholar
  24. 24.
    Chiu MC, Pun CS, Wong HY (2017) Big data challenges of high-dimensional continuous-time mean-variance portfolio selection and a remedy. Risk Analysis 37(8):1532CrossRefGoogle Scholar
  25. 25.
    Chen Jianguo, Li Kenli, Deng Qingying, Li Keqin, Yu Philip S (2019) Distributed deep learning model for intelligent video surveillance systems with edge computing. IEEE Trans Ind Inf.
  26. 26.
    Yu L, Chen H, Wang S (2009) Evolving least squares support vector machines for stock market trend mining. IEEE Trans Evol Comput 13(1):87–102CrossRefGoogle Scholar
  27. 27.
    Ebrahimpour R, Nikoo H, Masoudnia S (2011) Mixture of MLP-experts for trend forecasting of time series: a case study of the tehran stock exchange. Int J Forecast 27(3):804–816CrossRefGoogle Scholar
  28. 28.
    Chen MY, Chen BT (2015) A hybrid fuzzy time series model based on granular computing for stock price forecasting. Inf Sci 294(2):227–241MathSciNetCrossRefGoogle Scholar
  29. 29.
    Chen Jianguo, Li Kenli, Bilal Kashif, Zhou Xu, Li Keqin, Yu Philip S (2018) A bi-layered parallel training architecture for large-scale convolutional neural networks. IEEE Trans Parallel Distrib Syst 30(5):965–976. CrossRefGoogle Scholar
  30. 30.
    Chen J, Li K, Huigui R, Bilal K, Li K, Yu PS (2018) A periodicity-based parallel time series prediction algorithm in cloud computing environments. Inf Sci.
  31. 31.
    Bengio Y, Delalleau O (2009) Justifying and generalizing contrastive divergence. Neural Comput 21(6):1601MathSciNetzbMATHCrossRefGoogle Scholar
  32. 32.
    Cao Z, Long C, Chao Z (2015) Spiking neural network-based target tracking control for autonomous mobile robots. Neural Comput Appl 26(8):1839–1847CrossRefGoogle Scholar
  33. 33.
    Dahl GE, Sainath TN, Hinton GE (2013) Improving deep neural networks for LVCSR using rectified linear units and dropout. In: IEEE international conference on acousticsGoogle Scholar
  34. 34.
    Qian B, Rasheed K (2007) Stock market prediction with multiple classifiers. Appl Intell 26(1):25–33CrossRefGoogle Scholar
  35. 35.
    Fratianni M, Marchionne F (2013) The fading stock market response to announcements of bank bailouts. J Financ Stabil 9(1):69–89CrossRefGoogle Scholar
  36. 36.
    Patwary EU, Lee JY, Nobi A (2017) Changes of hierarchical network in local and world stock market. J Kor Phys Soc 71(7):444–451CrossRefGoogle Scholar
  37. 37.
    Wu X, Lu H (2010) Exponential synchronization of weighted general delay coupled and non-delay coupled dynamical networks. Comput Math Appl 60(8):2476–2487MathSciNetzbMATHCrossRefGoogle Scholar
  38. 38.
    Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436CrossRefGoogle Scholar
  39. 39.
    Song Y, Lee JW, Lee J (2018) A study on novel filtering and relationship between input-features and target-vectors in a deep learning model for stock price prediction. Appl Intell 49:897–911CrossRefGoogle Scholar
  40. 40.
    Pang X, Zhou Y, Pan W (2018) An innovative neural network approach for stock market prediction. J Supercomput 1:1–21Google Scholar
  41. 41.
    Asadi S, Hadavandi E, Mehmanpazir F (2012) Hybridization of evolutionary Levenberg-Marquardt neural networks and data pre-processing for stock market prediction. Knowledge-Based Syst 35(15):245–258CrossRefGoogle Scholar
  42. 42.
    Yu-Hui T, Wei K, Shou-Ning Q (2010) Research on stock quotation based on improved rough lattice model. IEEE 3:442–445Google Scholar
  43. 43.
    Yoo PD, Kim MH, Jan T (2005) Financial forecasting: advanced machine learning techniques in stock market analysis. IEEE, 1–7Google Scholar
  44. 44.
    O’Connor N, Madden MG (2006) A neural network approach to predicting stock exchange movements using external factors. Knowledge-Based Syst 19(5):371–378CrossRefGoogle Scholar
  45. 45.
    Chen Yuedan, Li Kenli, Yang Wangdong, Xiao Guoqing, Xie Xianghui, Li Tao (2019) Performance-aware model for sparse matrix-matrix multiplication on the sunway TaihuLight supercomputer. IEEE Trans Parallel Distrib Syst 30(4):923–938CrossRefGoogle Scholar
  46. 46.
    Maknickiené N, Maknickas A (2013) Financial market prediction system with Evolino neural network and Delphi method. Physiologia Plantarum 14(2):403–413Google Scholar
  47. 47.
    Jie W, Wang J (2017) Forecasting stochastic neural network based on financial empirical mode decomposition. Neural Netw 90:8–20CrossRefGoogle Scholar
  48. 48.
    Xiao Guoqing, Li Kenli, Li Keqin (2017) Reporting l most influential objects in uncertain databases based on probabilistic reverse top-k queries. Inf Sci 405:207–226CrossRefGoogle Scholar
  49. 49.
    Desai VS, Bharati R (2010) The efficacy of neural networks in predicting returns on stock and bond indices. Decis Sci 29(2):405–423CrossRefGoogle Scholar
  50. 50.
    Xiao G, Li K (2019) CASpMV: a customized and accelerative SPMV framework for the sunway TaihuLight. IEEE Transactions on Parallel and Distributed Systems pp. 1–1.
  51. 51.
    Lin A, Shang P, Zhou H (2014) Cross-correlations and structures of stock markets based on multiscale MF-DXA and PCA. Nonlinear Dyn 78(1):485–494CrossRefGoogle Scholar
  52. 52.
    Statistical data: National bureau of statistics of china (nbsc). URL
  53. 53.
    iFind: Hithink flush information network co., ltd. (ifind). URL
  54. 54.
    CSMAR: Tai’an information technology co., ltd. (csmar). URL
  55. 55.
    Leshno M, Lin VY, Pinkus A (1991) Original contribution: multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Comput 6(6):861–867Google Scholar
  56. 56.
    Mandic DP, Chambers JA (1999) Relating the slope of the activation function and the learning rate within a recurrent neural network. Neural Comput 11(5):1069–1077CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of AccountingFujian Jiangxia UniversityFuzhouChina

Personalised recommendations