Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks

Proceedings of NAACL-HLT 2016, pages 374–379, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks Yangtuo Peng and Hui Jiang Department of Electrical Engineering and Computer Science, York University, 4700 Keele Street, Toronto, Ontario, M3J 1P3, Canada emails: tim@cse.yorku.ca, hj@cse.yorku.ca Abstract Financial news contains useful information on public companies and the market. In this pa- per we apply the popular word embedding methods and deep neural networks to lever- age financial news to predict stock price move- ments in the market. Experimental results have shown that our proposed methods are simple but very effective, which can signifi- cantly improve the stock prediction accuracy on a standard financial database over the base- line system using only the historical price in- formation. 1 Introduction In the past few years, deep neural networks (DNNs) have achieved huge successes in many data mod- elling and prediction tasks, ranging from speech recognition, computer vision to natural language processing. In this paper, we are interested in apply- ing the powerful deep learning methods to financial data modelling to predict stock price movements. Traditionally neural networks have been used to model stock prices as time series for the forecast- ing purpose, such as in (Kaastra and Boyd, 1991; Adya and Collopy, 1991; Chan et al., 2000; Skabar and Cloete, 2002; Zhu et al., 2008). In these earlier work, due to the limited training data and computing power available back then, normally shallow neural networks were used to model various types of fea- tures extracted from stock price data sets, such as historical prices, trading volumes, etc, in order to predict future stock yields and market returns. More recently, in the community of natural lan- guage processing, many methods have been pro- posed to explore additional information (mainly on- line text data) for stock forecasting, such as financial news (Xie et al., 2013; Ding et al., 2014), twitter sentiments (Si et al., 2013; Si et al., 2014), finan- cial reports (Lee et al., 2014). For example, (Xie et al., 2013) has proposed to use semantic frame parsers to generalize from sentences to scenarios to detect the roles of specific companies (positive or negative), where support vector machines with tree kernels are used as predictive models. On the other hand, (Ding et al., 2014) has proposed to use various lexical and syntactic constraints to extract event fea- tures for stock forecasting, where they have inves- tigated both linear classifiers and deep neural net- works as predictive models. In this paper, we propose to use the recent word embedding methods (Mikolov et al., 2013b; Liu et al., 2015; Chen et al., 2015) to select features from on-line financial news corpora, and employ deep neural networks (DNNs) to predict the future stock movements based on the extracted features. Exper- imental results have shown that the features derived from financial news are very useful and they can significantly improve the prediction accuracy over the baseline …

Content truncated to 500 words