In recent years, the rapid development of machine learning has made it go into the field of stocks prediction. There have already been a few mature algorithms in the world that could help analyze the futural movements of the stocks market. In this paper, the author aims to exploit the effectiveness of machine learning methods in stock prediction. The utilized algorithms contain SOM(Self-organizing Maps) and SVR(Support vector regression) SVM, RNN, LSTM as well as work on several papers from others to estimate the probable advantages or disadvantages of the algorithms. After these experiments and testing, the author finds out some conclusions about the algorithms and realizes that the SOM algorithm has the advantage of exploiting the neighbor relationship on the cluster centroids is beneficial to the interpretation of the clustering results while having the disadvantage that users must select parameters, neighbor function, grid type and number of centroids.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.