Research Article
An Enterprise Investment Method Integrated with Improved Feature Optimization and Stochastic Configuration Networks
@INPROCEEDINGS{10.4108/eai.19-5-2023.2334425, author={Qiang Zhang and DongQiang Wang}, title={An Enterprise Investment Method Integrated with Improved Feature Optimization and Stochastic Configuration Networks}, proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2023}, month={7}, keywords={machine learning stochastic configuration networks data mining}, doi={10.4108/eai.19-5-2023.2334425} }- Qiang Zhang
DongQiang Wang
Year: 2023
An Enterprise Investment Method Integrated with Improved Feature Optimization and Stochastic Configuration Networks
ICBBEM
EAI
DOI: 10.4108/eai.19-5-2023.2334425
Abstract
To solve the problem that enterprise investment analysis is challenging to analyze efficiently and accurately, this paper proposed a new method based on artificial intelligence method to process amounts of data and make behavioral predictions. Efficient investment promotion has a great impact on the future economic benefits of a company or industrial park. The data used in this paper is derived from the CCCC Industry Operational Platform. Firstly, a multidimensional feature set of enterprise data is gathered and defined that a shareholding ratio greater than 50% indicates investment behavior by the enterprise. Secondly, normalization methods are adopted to organize the multidimensional feature set, reducing differences in magnitude between variables and optimizing model computational efficiency. Finally, the SCN algorithm is utilized to predict enterprise investment behaviors. Finally, taking two industries as the training data. The experiment shows that the precision of predicting the investment behavior of scientific research enterprises reaches 93.95%, and the precision of predicting the investment behavior of information transmission enterprises reaches 90.45%. Meanwhile, comparative experiments have proven that the method proposed in this article not only directly improves the efficiency of the enterprise investment analysis process, but also enhances the accuracy of enterprise investment analysis.
