Research on the Contribution of Regional Import and Export Influential Factors Based on RBF Neural Network

Yifan Xu; Mohan Chen; Jinyanxi Zhao

doi:10.54097/hbem.v12i.8314

Authors

Yifan Xu
Mohan Chen
Jinyanxi Zhao

DOI:

https://doi.org/10.54097/hbem.v12i.8314

Keywords:

RBF neural network, Zhejiang Province, Regional Import, Influential Factors.

Abstract

Since the reform and opening up, the proportion of imports and exports in all provinces in China has increased to a great extent, and the total import and export volume is an important condition for reflecting the economic level of a region, and it is also one of the important influencing factors affecting economic growth. In the context of economic development, by analyzing what are the factors affecting import and export, the contribution of import and export to economic growth and the reasons for promoting economic development can be analyzed. Based on this, this paper selects Zhejiang Province as the research object, uses the data from 1990 to 2020, and uses the RBF neural network algorithm to analyze this series of data. In this paper, multiple secondary indicators are selected from the five perspectives of population, industrial structure, economic development level, currency, and science and technology, and RBF training is carried out, and it is found that when the model parameter is 19, the model accuracy converges and the algorithm reaches the optimal value. According to the algorithm results, we conclude that the methods to increase the total import and export volume of the region include implementing an expansionary fiscal policy and increasing the total budget expenditure; Increase research and development funding, such as university research funding and talent subsidies; Increase industrial output value, such as providing assistance and subsidies to industrial enterprises for export orientation.

Downloads

Download data is not yet available.

References

Jia Qianying Empirical analysis of domestic carbon financial transaction risk based on financial time series analysis [D]. Shandong University, 2022.

Wang Siqi, Wang Ziwei. Prediction and Prevention of Regional Financial Risks in Hunan [J]. China Foreign Investment, 2022 (08): 65 - 67.

Tu Rui Credit Risk Assessment of Listed SMEs Based on Logistic RBF NN Hybrid Two stage Model [D]. Hangzhou University of Electronic Science and Technology, 2022.

Wan Ajun, Li Lianfa Whether machines can act as human central bankers -- A discussion on the theoretical basis and practice of applying machine learning methods to monetary policy [J]. Shanghai Finance, 2021 (09): 34 - 46.

Zhao Boyu Combination Research of Machine Learning in Exchange Rate Forecasting [D]. Zhejiang University, 2021.

Xu Zhong A Study on the Price Linkage between Crude Oil Futures and Spot Markets [D]. Nanjing Audit University, 2021.

Huang Sijie, Li Causality. Research on Regional Financial Risk Prediction in Jiangsu Province Based on RBF Neural Network Model [J]. Operation and Management, 2021 (05): 168 - 172.

Liu Shumei, Zhu Yijia, Xu Nanshan. Application of improved RBF neural network algorithm in financial time series prediction [J]. Computer System Application, 2019, 18 (11): 176 - 178+186.

Sun Bin, Li Tieke, Zhang Wenwen. Research on financial stock index prediction and financial nonlinear system identification based on DFNN [J]. China Management Informatization, 2009,12 (21): 89 - 92.

Sun Yanfeng, Liang Yanchun, Jiang Jingqing, Wu Chunguo. Neural network method in financial time series prediction [J]. Journal of Jilin University (Information Science Edition), 2004 (01): 49 - 52.

Wu S, Chow T. Induction machine fault detection using SOM-based RBF neural networks[J]. IEEE Transactions on Industrial Electronics, 2022, 51 (1):183 - 194.

Klayman, JoshuaHa, Young-won. Confirmation, disconfirmation, and information in hypothesis testing. [J]. Psychological Review, 2017.