A novel (U)MIDAS-SVR model with multi-source market sentiment for forecasting stock returns.
Qifa XuLiukai WangCuixia JiangYezheng LiuPublished in: Neural Comput. Appl. (2020)
Keyphrases
- stock returns
- multi source
- financial time series
- stock market
- chinese stock market
- data fusion
- information fusion
- stock price
- exchange rate
- cross sectional
- short term
- developed countries
- financial data
- sentiment analysis
- non stationary
- stock exchange
- multiple sources
- financial markets
- data integration
- garch model
- wavelet support vector machine
- stock data
- sentiment classification
- data sources
- multivariate time series
- long term
- developing countries
- community detection
- information integration
- supervised learning
- cash flow
- data model
- social networks