Promoting Financial Market Development-Financial Stock Classification Using Graph Convolutional Neural Networks

According to surveys, one in seven people China are involved stock trading, and the role of stocks global economy is growing. In terms entire market, Chinese market alone has over 4000 stocks. Faced with a chaotic diverse assortment stocks, it necessary categorize them. On hand, can facilitate research, on other, make easier for stockholders purchase shares. The graph convolutional neural network-based SK-GCN model developed this paper delivers excellent results categorization classes. This employs two layers activation functions effectively by incorporating external nodes expand features drawing inspiration from short text classification. strategy highly innovative produces promising outcomes. paper, we constructed dataset crawling information all listed GEM Oriental Fortune website. We achieved an accuracy 83.04% macro-F1 value 0.8303 under assumption small sample training, its classification effect significantly superior other models.