Abstract
The number and trade volume of Chinese firms are increasing year by year. The resulting variety of complex transactions have made risk control and government supervision difficult. China’s listed companies have specific classifications, but most non-listed companies do not have comparable classifications, making it difficult to analyze all companies on the same basis. Supply chain networks have proved to contain rich information, which can more completely reflect transaction relationships. This study mines hidden information obtained from the supply chain network to classify participating companies. We construct the supply chain network data set of listed companies, and use the graph neural network (GNN) algorithm to classify these companies. Experiments show that this method is effective and can produce better results than the commonly used machine learning methods. On average the accuracy of industry classification for listed companies is improved by over 2%, and time required is greatly reduced. In addition, we use economic variables derived from supply chain concepts to try to explain the effectiveness and economic significance of GNN, and find that GNN can also be used to classify companies into multiple industries. Our findings provide new insights, as well as a potential method to label a private company’s industry using only public text information, which can be used for the study of smart industry classification and mining implicit information from the perspective of supply chain networks.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.