Abstract
Innovation and entrepreneurship as the core development mode is the only way to continue my country's economic development. Therefore, research on the synergistic impact of innovation on China's economic development is of great significance. With the continuous development of sharing economy, Internet finance, and other fields, the digital economy is reshaping the entire social ecology and becoming an important part of the national economy. Aiming at China’s digital economy, this article takes the Shanghai Composite Index and three listed stocks in the stock market as examples, collects the closing data of the Shanghai Composite Index and the stock market prices of three listed companies as sample data, uses the BP neural network prediction model and the optimized particle swarm optimization-neural networks (PSO-BP) neural network model predicts the future trends of the Shanghai Composite Index and the three stocks, respectively. Compared with other models, PSO-BP requires fewer parameters and draws more accurate conclusions. It is a model that is very suitable for digital economic forecasting. The experimental results show that the prediction effect of the PSO-BP neural network is higher than that of the BP neural network prediction model obtained by the two prediction models in the prediction process of the Shanghai Composite Index; the error rate of the BP neural network prediction model in the three listed stocks 6.37%, 3.01%, 9.85%; PSO-BP neural network prediction model predicts the future trend of the three listed stocks with error rates of 3.21%, 0.37%, and 0.89%. After comparing and analyzing the results of the forecast error value, it is concluded that the PSO-BP neural network forecast model has a more accurate forecast of stock prices and smaller errors, and the forecast of future trends is also consistent with actual trends.
Similar content being viewed by others
References
Qi X, Cheng Gengguo XuXu (2019) Research on stock prediction model based on neural network ensemble learning. Comput Eng Appl 55(08):238–243
Zhou N, Kai R (2019) Research and prediction of RMB exchange rate based on machine learning integration model. Financ Econ 508(10):102–104
Lisheng Y, Shengqi T, Sheng Li et al (2019) Traffic flow forecasting based on integrated moving average autoregressive and genetic particle swarm optimization wavelet neural network combined model. J Electron Inf Technol 041(009):2273–2279
Yiyong Ye (2016) Guangdong province’s tertiary industry output value forecast based on combination forecast model. Econ Math 33(002):50–56
Ruijiao Y, Siqing Y (2018) Microblog user credit evaluation model based on selective neural network integration. Comput Eng Des 39(05):286–291
Fengping Y, Dabin Z (2016) Construction of user preference model based on differential evolution neural network. Microcomput Appl 35(08):44–47
Binyan W, Junfeng T, Lisha C et al (2018) Spatial differentiation and influencing factors of China’s digital economy. Geogr Sci 038(006):859–868
Xiaoyi W, Yajing Z (2020) Development status and international competitiveness of China’s digital economy. Sci Res Manag 41(05):252–260
Crabtree A, Lodge T, Colley J et al (2016) Enabling the new economic actor: data protection, the digital economy, and the Databox. Pers Ubiquit Comput 20(6):947–957
Kulyasova EV, Trifonov PV (2020) Development of forms of interaction between universities and the business community in the digital economy. Strateg Decis Risk Manag 11(2):216–223
Boev AG (2020) The contents and peculiarities of the process of institutional transformation of industrial complexes in a digital economy. Russ J Ind Econ 13(1):18–28
Liangliang Z, Xiaofeng L, Zhi C (2018) Strategic thinking on the development of china’s digital economy. Modern Manag Sci 302(05):90–92
Hongli M, Jingjing G, Hequan W (2019) 5G is an important engine in China’s digital economy era. China Inform Ind 333(03):14–17
Dazheng L (2019) Research on Shanghai stock exchange 50 index based on Bayesian integrated neural network. Sci Technol Innov Herald 16485(17):148–150
Huimin Z, Jiangtao L, Junchao Y et al (2016) Research and application of integrated BP neural network prediction model. Telecommun Sci 32(002):60–67
Cheng C, Furong S, Haiyuan X et al (2018) Extraction of overhead iron tower slope protection based on convolutional neural network. Sci Technol Innov 115(19):44–47
Liu Xiaobao Lu, Hongbiao YY et al (2020) Research on distributed resource spatial text classification based on multivariate neural network fusion. Comput Integr Manuf Syst 026(001):161–170
Weiguo S, Pengxiao S (2016) A niche-based negative correlation neural network ensemble algorithm. J Zhejiang Univ Technol 44(005):482–486
Zhaoyu H, Yong Z, Bing L (2019) Named entity recognition method based on differential neural network integration. Comput Eng Des 40(04):101–107
Pengfei K, Maoguo C, Tao W (2020) Face recognition algorithm based on improved convolutional neural network and integrated learning. Computer Engineering 046(002):262–267
Hengde Z, Tingyu Z, Tao Li et al (2018) Multi-model integrated forecast of pollutant concentration based on BP neural network. China Environ Sci 38(4):1243–1256
Yuquan Li (2018) Handwritten character recognition based on ensemble learning improved convolutional neural network. Electr Technol Softw Eng 131(09):183
Rong L, Xinnong H, Xiaoguo H et al (2018) Application and prospect of artificial intelligence technology in intelligent livestock and poultry farms. Tianjin Agric Sci 153(07):38–44
Haiting H, Linlin Y, Xiangrui Li et al (2019) Research on data capitalization in digital economy. Credit Investig 37(04):72–78
Jianguang S (2020) Investment in the field of digital economy is huge: thinking about digital transformation under the epidemic. China Econ Trade Guide 969(10):34–35
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There no potential competing interests in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jiang, Y. Prediction model of the impact of innovation and entrepreneurship on China's digital economy based on neural network integration systems. Neural Comput & Applic 34, 2661–2675 (2022). https://doi.org/10.1007/s00521-021-05899-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05899-7