A new graphic kernel method of stock price trend prediction based on financial news semantic and structural similarity.
Wen LongLinqiu SongYing-jie TianPublished in: Expert Syst. Appl. (2019)
Keyphrases
- financial news
- stock price
- structural similarity
- kernel methods
- financial time series
- stock market
- structural information
- non stationary
- historical data
- kernel function
- support vector
- quality metrics
- short term
- machine learning
- semantic information
- support vector machine
- news articles
- feature space
- natural language
- information extraction
- long term
- news stories