Stock Price Prediction Using Attention-based Multi-Input LSTM

Hao Li, Yanyan Shen, Yanmin Zhu
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:454-469, 2018.

Abstract

Stock price prediction has always been a hot but challenging task due to the complexity and randomness in stock market. Investors and researchers usually derive a great number of factors from original data such as historical stock price, company profit, or textual data collected from social media. Normally these factors are then fed into models like linear regression, SVM or neural networks to make a prediction. Even though the number of factors are considerable, most of them have relatively weak correlations with future stock price. During training process, these factors not only result in additional computation but sometimes even be harmful to the performance of prediction. In this paper, we propose a novel multi-input LSTM model which is capable of extracting valuable information from low-correlated factors and discarding their harmful noise by employing extra input gates controlled by the convincing factors called \emph{mainstream}. We also introduce several new factors including the prices of other related stocks to improve the prediction accuracy. The experimental results on the stock data from China stock market demonstrate the effectiveness of the proposed approach compared with the state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-li18c, title = {Stock Price Prediction Using Attention-based Multi-Input LSTM}, author = {Li, Hao and Shen, Yanyan and Zhu, Yanmin}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {454--469}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/li18c/li18c.pdf}, url = {https://proceedings.mlr.press/v95/li18c.html}, abstract = {Stock price prediction has always been a hot but challenging task due to the complexity and randomness in stock market. Investors and researchers usually derive a great number of factors from original data such as historical stock price, company profit, or textual data collected from social media. Normally these factors are then fed into models like linear regression, SVM or neural networks to make a prediction. Even though the number of factors are considerable, most of them have relatively weak correlations with future stock price. During training process, these factors not only result in additional computation but sometimes even be harmful to the performance of prediction. In this paper, we propose a novel multi-input LSTM model which is capable of extracting valuable information from low-correlated factors and discarding their harmful noise by employing extra input gates controlled by the convincing factors called \emph{mainstream}. We also introduce several new factors including the prices of other related stocks to improve the prediction accuracy. The experimental results on the stock data from China stock market demonstrate the effectiveness of the proposed approach compared with the state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Stock Price Prediction Using Attention-based Multi-Input LSTM %A Hao Li %A Yanyan Shen %A Yanmin Zhu %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-li18c %I PMLR %P 454--469 %U https://proceedings.mlr.press/v95/li18c.html %V 95 %X Stock price prediction has always been a hot but challenging task due to the complexity and randomness in stock market. Investors and researchers usually derive a great number of factors from original data such as historical stock price, company profit, or textual data collected from social media. Normally these factors are then fed into models like linear regression, SVM or neural networks to make a prediction. Even though the number of factors are considerable, most of them have relatively weak correlations with future stock price. During training process, these factors not only result in additional computation but sometimes even be harmful to the performance of prediction. In this paper, we propose a novel multi-input LSTM model which is capable of extracting valuable information from low-correlated factors and discarding their harmful noise by employing extra input gates controlled by the convincing factors called \emph{mainstream}. We also introduce several new factors including the prices of other related stocks to improve the prediction accuracy. The experimental results on the stock data from China stock market demonstrate the effectiveness of the proposed approach compared with the state-of-the-art methods.
APA
Li, H., Shen, Y. & Zhu, Y.. (2018). Stock Price Prediction Using Attention-based Multi-Input LSTM. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:454-469 Available from https://proceedings.mlr.press/v95/li18c.html.

Related Material