Using Structured Events to Predict Stock Price Movement: An Empirical Investigation

By Xiao Ding, Ting-Wei Liu, Junwen Duan. 2014

256 citations recorded by the source corpus.

It has been shown that news events influence the trends of stock price movements. However, previous work on news-driven stock market prediction rely on shallow features (such as bags-of-words, named entities and noun phrases), which do not capture structured entity-relation information, and hence cannot represent complete and exact events. Recent advances in Open Information Extraction (Open IE) techniques enable the extraction of structured events from web-scale data. We propose to adapt Open IE technology for event-based stock price movement prediction, extracting structured events from large-scale public news without manual efforts. Both linear and nonlinear models are employed to empirically investigate the hidden and complex relationships between events and the stock market. Largescale experiments show that the accuracy of S&P 500 index prediction is 60%, and that of individual stock prediction can be over 70%. Our event-based system outperforms bags-of-words-based baselines, and previously reported systems trained on S&P 500 stock historical data.

Subfields: Economics and Econometrics, Management Science and Operations Research, Signal Processing, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

In Signal Processing

In Time-Series & Forecasting

Citations in the corpus

Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network (2018, methodology): “Ding et al. [18] proposed using Open Information Extraction for event-based stock price trend prediction to extract structured events from large-scale public news articles; the structured event was denoted as (O 1 , P, O 2 ) where O 1 is the ﬁrst object (ticker name, company name, etc.), O 2 is the…”
Stock Price Prediction by Deep Neural Generative Model of News Articles (2018, methodology): “Just as in the previous studies [12], [24], we only extracted the titles from these news articles.”
Improving stock market prediction via heterogeneous information fusion (2017, methodology): “Previous work [4] show that news titles are more useful to extract events compared to news contents.”
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks (2015, methodology): “On the other hand, (Ding et al., 2014) has proposed to use various lexical and syntactic constraints to extract event features for stock forecasting, where they have investigated both linear classifiers and deep neural networks as predictive models.”
Temporal Relational Ranking for Stock Prediction (2018, unknown): “Under a similar classification setting, another line of research is classifying the trend of a stock from relevant financial news reports [9, 10, 20, 38, 51].”
Stock Movement Prediction from Tweets and Historical Prices (2018, methodology): “With the prevalence of deep neural networks (Le and Mikolov, 2014), eventdriven approaches were studied with structured event representations (Ding et al., 2014, 2015).”
Stock Market Prediction with Deep Learning: A Character-based Neural Language Model for Event-based Trading (2017, methodology): “• E-NN: structured events tuple input and standard neural network prediction model (Ding et al., 2014).”
Applications of deep learning in stock market prediction: recent progress (2020, methodology): “Ding et al. (2015) uses a neural tensor network to learn event embeddings for representing news documents. Hu et al. (2018b) uses a news embedding layer to encode each news into a news vector. Wang et al. (2019b) uses a convolution neural network (CNN) layer to extract salient features from transfor”
Detecting, quantifying and accessing impact of news events on Indian stock indices (2017, methodology): “The daily and weekly accuracy achieved using LSTM based algo-rithm is comparable with prediction accuracy reported by [6] Ding et. al. in their work on event based stock prediction of Standard & Poor 500 stock index.”
Knowledge-Driven Event Embedding for Stock Prediction (2016, methodology): “We use publicly available ﬁnancial news from Reuters and Bloomberg over the period from October 2006 to November 2013, released by Ding et al. (2014).”
Deep learning for stock prediction using numerical and textual information (2016, methodology): “[9] employed SVM and deep neural network, respectively, although these models consider the influence of past events to have a fixed duration.”
A New Model for Stock Price Movements Prediction Using Deep Neural Network (2017, methodology): “[9] reports a system that uses structured event tuples ( O i , P, T ), where O i ⊆ O is a set of objects, P is a relation over the objects and T is a time interval.”
Deep Learning for Event-Driven Stock Prediction (2015, methodology): “We follow our previous work [Ding et al., 2014] and represent an event as a tupleE = (O1, P,O2, T ), whereP is the action, O1 is the actor and O2 is the object on which the action is performed.”