News-Driven Stock Prediction With Attention-Based Noisy Recurrent State Transition

Abstract

We consider direct modeling of underlying stock value movement sequences over time in the news-driven stock movement prediction. A recurrent state transition model is constructed, which better captures a gradual process of stock movement continuously by modeling the correlation between past and future price movements. By separating the effects of news and noise, a noisy random factor is also explicitly fitted based on the recurrent states. Results show that the proposed model outperforms strong baselines. Thanks to the use of attention over news events, our model is also more explainable. To our knowledge, we are the first to explicitly model both events and noise over a fundamental stock value state for news-driven stock movement prediction.

Deep Multiple Instance Learning for Forecasting Stock Trends using Financial NewsDeep Multiple Instance Learning for Forecasting Stock Trends using Financial News

“…Xu Y et al [44] propose a stock price prediction model with the aid of news event detection and sentiment orientation analysis, through introducing Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM) in their predictive model. Most recently, a recurrent state transition model, integrating the influence of news events and random noises over a fundamental stock value state, is constructed in [45] for the task of news-driven stock movement prediction. A tensor-based information framework for predicting stock movements in response to new information is also introduced in [46].…”

Multiple Instance Learning Networks for Stock Movements Prediction with Financial News

“…Xu Y et al [45] propose a stock price prediction model with the aid of news event detection and sentiment orientation analysis, through introducing Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM) in their predictive model. Most recently, a recurrent state transition model, integrating the influence of news events and random noises over a fundamental stock value state, is constructed in [46] for the task of news-driven stock movement prediction. A tensor-based information framework for predicting stock movements in response to new information is also introduced in [47].…”

From Text Representation to Financial Market Prediction: A Literature Review

“…Recently, scholars [18,22,79,122,129,133] have used the word2vec [5] or Doc2vec [4] representation of news headlines and content in their financial decision support systems; however, transformer-based language models [6,130] have shown better results in reflecting deep semantic and syntactic news information compared to traditional word embedding in the financial domain. Liu, in [35], used long-term and short-term event embedding methods which contain the stack ELMO embedding of the t-days set of news headlines for the prediction of the S&P500 index. The authors of [21,25,35] used BERT-contextualized word embedding representation for market prediction.…”

“…Liu, in [35], used long-term and short-term event embedding methods which contain the stack ELMO embedding of the t-days set of news headlines for the prediction of the S&P500 index. The authors of [21,25,35] used BERT-contextualized word embedding representation for market prediction. Farimani et al [16] proposed contextaware conceptual document representation to model the relevance between the news based on all the information in financial news titles and bodies via the clustering of contextualized BERT word embedding.…”

“…Text mining techniques, such as a sentiment analysis [10][11][12][13], part of speech tagging (POS) [14,15], text representation, such as transformer-based word embedding [16][17][18][19][20][21][22], and machine learning techniques [23][24][25][26][27][28][29][30][31], have been used in this area after 2006. Recently, researchers have focused on using deep learning-based natural language processing (NLP), such as Bidirectional Encoder Representations from Transformer (BERT) [18,21,[32][33][34] or seq2seq architecture with an attention mechanism [20,[35][36][37][38], to structure textual web data. BERT-contextualized word embedding, announced by Google in 2018, is used as a word sense disambiguation technique for summarizing and selecting important news for investors' behavior analysis [21,25].…”