In general understanding, shareholders tend to think that there is a strong linkage between the stock prices of several listed companies of the same parent company. However, there is a lot of noise in stock data, which makes it difficult for the general linear classification method to achieve better prediction results. Therefore, the idea of predicting stock price derives two kinds: one is the idea of feature expansion, taking into account as much as possible the factors of stock price linkage, and the other is the idea of feature streamlining, which only retains important features for analysis
正在翻译中..