Download pdf
Stock Price Prediction Based on ARIMA and Neural Network
- 1 College of Art and Science, New York University, New York, US
* Author to whom correspondence should be addressed.
Abstract
The stock price is affected by many factors and is a very complex nonlinear and non-stationary system. Predicting stock prices is a classic problem. People hope to predict stock prices more accurately, so as to make profits through stocks. This article selects five stocks in the Nasdaq stock market from 2020 to 2023, and tries to use 3 AI models (ARIMA, CNN, LTSM) to predict and analyze their next day’s closing prices and use the RMSE as the index to analyze the prediction performance. This paper finds that the three models can predict the stock price next day well, among which the ARIMA model and LSTM model have better prediction results, average RMSE for them are about 3.3 and 4.5 while the CNN model has poorer prediction performance with RMSE 7.2. At the same time, paper is found that when the model has a turning point for the stock, all the models predict poorly. In the future, we can consider combining the eigenvalues of more stocks to reduce the impact of turning points on price prediction.
Keywords
stock price prediction, ARIMA, neural network
[1]. Vasilev, I., Slater, D., Spacagna, G., Roelants, P., and Zocca, V. (2019). Python Deep Learning: Exploring deep learning techniques and neural network architectures with Pytorch, Keras, and TensorFlow. Packt Publishing Ltd.
[2]. Devi, B. U., Sundar, D., and Alli, P. (2013). An effective time series analysis for stock trend prediction using ARIMA model for nifty midcap-50. International Journal of Data Mining & Knowledge Management Process, 3(1), 65.
[3]. Pai, P., and Hong, W. (2005). An improved neural network model in forecasting arrivals. Annals of Tourism Research, 32(4), 1138-1141.
[4]. Liang, J., Song, W., and Wang, M. (2011). Stock price prediction based on procedural neural networks. Advances in Artificial Neural Systems.
[5]. Ma, Q. (2020). Comparison of ARIMA, ANN and LSTM for stock price prediction. In E3S Web of Conferences, 218, 01026.
[6]. Siami-Namini, S., Tavakoli, N., and Namin, A. S. (2018). A comparison of ARIMA and LSTM in forecasting time series. In 2018 17th IEEE international conference on machine learning and applications, 1394-1401.
[7]. Mehtab, S., and Sen, J. (2020). Stock price prediction using convolutional neural networks on a multivariate timeseries. arXiv preprint arXiv:2001.09769.
[8]. Sen, J., and Mehtab, S. (2022). Stock price prediction using convolutional neural networks. Machine Learning in the Analysis and Forecasting of Financial Time Series, 68-101.
[9]. Sun, Y. (2023). Optimization of Convolutional neural network. Proceedings of the 37th China (Tianjin) 2023 'IT, Network, Information Technology, Electronics, Instrument and Meter Innovation Academic Conference, 54-57.
[10]. Chen, K., Zhou, Y., and Dai, F. (2015). A LSTM-based method for stock returns prediction: A case study of China stock market. In 2015 IEEE international conference on big data, 2823-2824.
Cite this article
Liao,X. (2023). Stock Price Prediction Based on ARIMA and Neural Network. Advances in Economics, Management and Political Sciences,56,163-171.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Financial Technology and Business Analysis
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).