Comparative Analysis of ARIMA Model and Neural Network in Predicting Stock Price
ARIMA model is a time series model, which is used to analyze and predict the mean value of the sequence. Neural network can be used to predict in various fields. In this essay, the neural network algorithm is used for the financial time series to predict the trend of stock price change, and the results are compared with the traditional ARIMA. It is found that the neural network algorithm can better predict the change of stock price. In the empirical analysis, Python is used to establish three models for analysis and prediction, which can provide a more appropriate model reference for investors to judge the short-term trend of stock prices and portfolio decision-making.
KeywordsARIMA model The neural network Prediction
- 1.Schumann, M., Lohrbach, T.: Comparing artificial neural networks with statistical methods within the field of stock market prediction. In: Proceeding of the Twenty-Sixth Hawaii International Conference on System Sciences, vol. 4, pp. 597–606 (1993)Google Scholar
- 3.Xiong, R., Nichols, E.P., Shen, Y.: Deep learning stock volatility with google domestic trends (2015). arXiv preprint, arXiv:1512.04916
- 5.Heaton, J.B., Polson, N.G., Witte, J.H.: Deep Learning in Finance (2016). arXiv preprint, arXiv:1602.06561
- 6.Specht, D.F.: A general regression neural network. Revue De Physique Appliquée. 2(6), 1321–1325 (1991)Google Scholar
- 8.Di Persio, L., Honchar, O.: Artificial Neural Networks Architectures for Stock Price Prediction: Comparisons and Applications. Int. J. Circuits Syst. Sign. Proces. 10, 403–413 (2016)Google Scholar