Financial news and stocks are correlated with each other, however such correlation is constantly changing overtime and depends on various internal and external factors. In this research, we have built a collection of company related news from Yahoo Financial News for the period October 1st 2014 to May 1st 2015, and financial data on the same 28 company stocks listed on the US stock market. We perform a series of Mantel tests between news and stocks from a sequence of 4 week sliding windows. The result provides quantitive support that there is a correlation between news content and stock price, which is better correlated with news than other parameters, such as daily return, volume or daily change.
|Title of host publication||IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)|
|Place of Publication||Athens|
|Publication status||Published - 13 Feb 2017|