A Novel Distributed Representation of News (DRNews) for Stock Market Predictions

Abstract

In this study, a novel Distributed Representation of News (DRNews) model is developed and applied in deep learning-based stock market predictions. With the merit of integrating contextual information and crossdocumental knowledge, the DRNews model creates news vectors that describe both the semantic information and potential linkages among news events through an attributed news network. Two stock market prediction tasks, namely the short-term stock movement prediction and stock crises early warning, are implemented in the framework of the attention-based Long Short Term-Memory (LSTM) network. It is suggested that DRNews substantially enhances the results of both tasks comparing with five baselines of news embedding models. Further, the attention mechanism suggests that short-term stock trend and stock market crises both receive influences from daily news with the former demonstrates more critical responses on the information related to the stock market per se, whilst the latter draws more concerns on the banking sector and economic policies.

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

“…A self-attention mechanism is applied to distribute attention to most relative words, news and days. Ma et al [37] develop a novel Distributed Representation of news (DRNews) through creating news vectors that describe both the semantic information and potential linkages among news events in an attributed news network. News vector representation has achieved state-of-art performances on various financial text classification tasks.…”

Multiple Instance Learning Networks for Stock Movements Prediction with Financial News

“…A self-attention mechanism is applied to distribute attention to most relative words, news and days. Ma et al [38] develop a novel Distributed Representation of news (DRNews) through creating news vectors that describe both the semantic information and potential linkages among news events in an attributed news network. News vector representation has achieved state-of-art performances on various financial text classification tasks.…”