Stock Index Prediction Based on Principal Component Analysis and Machine Learning

With the development of the secondary stock market and the increase of people's enthusiasm for stock investment, stock market investment has become a way for many people to make profits. Thus, the numerical prediction of stock price and stock index has become a hot topic of discussion and research in the market. In this paper, two advanced machine learning classification methods are adopted. The classification target is whether the stock price and stock index rise or fall on the next trading day. The classification criteria and models are formed by training set, and then the prediction effect is determined by prediction set. At the same time, the principal component analysis method is introduced to reduce the dimension of the classification characteristic index, reduce the input data, optimize the model construction, and then use the above two machine learning methods to train and predict, and observe the final results.