Improving stock market prediction via heterogeneous information fusion

Abstract

Traditional stock market prediction approaches commonly utilize the historical price-related data of the stocks to forecast their future trends. As the Web information grows, recently some works try to explore financial news to improve the prediction. Effective indicators, e.g., the events related to the stocks and the people's sentiments towards the market and stocks, have been proved to play important roles in the stocks' volatility, and are extracted to feed into the prediction models for improving the prediction accuracy. However, a major limitation of previous methods is that the indicators are obtained from only a single source whose reliability might be low, or from several data sources but their interactions and correlations among the multi-sourced data are largely ignored.In this work, we extract the events from Web news and the users' sentiments from social media, and investigate their joint impacts on the stock price movements via a coupled matrix and tensor factorization framework. Specifically, a tensor is firstly constructed to fuse heterogeneous data and capture the intrinsic * Corresponding author relations among the events and the investors' sentiments. Due to the sparsity of the tensor, two auxiliary matrices, the stock quantitative feature matrix and the stock correlation matrix, are constructed and incorporated to assist the tensor decomposition. The intuition behind is that stocks that are highly correlated with each other tend to be affected by the same event. Thus, instead of conducting each stock prediction task separately and independently, we predict multiple correlated stocks simultaneously through their commonalities, which are enabled via sharing the collaboratively factorized low rank matrices between matrices and the tensor. Evaluations on the China A-share stock data and the HK stock data in the year 2015 demonstrate the effectiveness of the proposed model.

Financial time series forecasting with deep learning : A systematic literature review: 2005–2019

“…In their proposed method, financial news, charts and social media tweets were used together to predict the stock price movement. The authors of [211] proposed a method that performed information fusion from several news and social media sources to predict the trend of the stocks. The authors of [212] proposed a novel method that used text mining techniques and Hybrid Attention Networks based on financial news for the forecast of the trend of stocks.…”

LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction

“…Xi Zhang et al [8] proposed that the investor social networks is also an emotion-oriented forecasting method, which utilizes emotional factors and stock correlation characteristics to model. In their further article [9], they considered the relationship between the single source and the multisource data and then employed the coupling matrix and tensor decomposition framework to study the impact of online news and user sentiment on stock price changes. In the research method of Huicheng Liu et al [10], an Attention-Based RNN was used to accomplish this task and a Bidirectional-LSTM is used to capture the characteristics of the information in the news text.…”

A Tensor-Based Sub-Mode Coordinate Algorithm for Stock Prediction

“… w s,i,j = { 1，i ≤ j and |y s,i -y s,j |/y s,j ≤ E 1 0 z , , denotes the similarity weight between the stock s and stock m at the time t. The stock correlation matrix Zt is obtained by the feature interaction method which is proposed in [17].…”