Stock price prediction based on ARIMA - SVM model
Download as PDF
Wenjuan Mei, Pan Xu, Ruochen Liu, and Jun Liu
Stock price is a complex non-stationary and non-linear time series, which is affected by economic cycle, financial policy, international environment and other factors, so the movement direction of stock price is unknown and complex. In order to accurately predict the trend of stock price, this paper proposes the ARIMA — SVM model, which is optimized and improved on the basis of the support vector machine model (SVM). Therefore, this model is able to process multi-dimensional nonlinear data. Firstly, ARIMA model was used to predict the data, and the error result obtained was used as the input variable of support vector machine (SVM). In the construction of SVM model, cross-validation method was used to traverse the search of parameter combination, and then the optimal parameter combination was determined, so as to predict the rise and fall trend and fluctuation direction of stock price. Through the empirical analysis of IBM stock, the accuracy of the model reaches 96.10%.
Support vector machine, ARIMA model, Stock price prediction