News and stock markets: A survey on abnormal returns and prediction models

Vast amount of news articles are published daily reflecting global topics. The stories represent information about events and expert opinions, which may trigger positive or negative expectations on the stock markets. The literature describes various methods for analyzing such correlations. In this paper we consider related approaches for tracking the impact of news on abnormal stock returns. In the first part we introduce studies with back- ground in Finance. Primarily by applying statistical functions the works examine unusual price volatilities and explore possible sources and market conditions, e.g. biased investors, limited attention, macro-economic variables, country development state, et cetera. In the second part we present studies with background in Computer Science, which take advan- tage of historic news and the equivalent market values. By following the common learning paradigm the projects elaborate prototypes for trend and stock price prediction. In the current survey we evaluate leading approaches regarding the objectives, assumptions, in- put, techniques, and performance. Moreover we provide a comparison framework of the recent prototypes and identify gaps for future research.