trading based on news strategy

Decision Support Systems

Highlights

•: Financial disclosures are the main source for the conclusion-making in finance.
•: Sentiment psychoanalysis of financial disclosures can provide decision support.
•: We design and compare different strategies for news trading.
•: These can outgo our benchmarks in terms of profits but at the cost of risk.
•: Especially viable approaches are supervised and reinforcement learning.

Abstract

The marvel of markets lies in the fact that dispersed information is instantaneously processed and used to adjust the price of goods, services and assets. Financial markets are particularly efficient when it comes to processing information; such information is typically embedded in textual news that is then taken aside investors. Quite recently, researchers have started to automatically determine news sentiment in society to explicate stock monetary value movements. Interestingly, this so-called news program sentiment deeds fairly well in explaining stock returns. In this paper, we design trading strategies that employ textual news show in order to obtain profits on the basis of new information entering the commercialise. We thus project approaches for automated decisiveness-devising settled connected supervised and reward learning. Altogether, we demonstrate how news show-based information can be incorporated into an investment system.

Keywords

Conclusion support

Financial news

Trading strategies

Text mining

Thought depth psychology

Trading simulation

Stefan Feuerriegel Stefan Feuerriegel is a post-doctoral research at Chair of Information Systems Research of the University of Freiburg with a focus on school tex minelaying and sentiment analysis of commercial enterprise news. Previously, he obtained his PhD point from the assonant inquiry institution. Atomic number 2 also holds a Master of Scientific discipline in Simulation Sciences from the RWTH Aachen University. He has co-authored research publications in the European Diary of Functional Search, Optimization Engineering, the Journal of Decision Systems and Determination Support Systems.

Helmut Prendinger Helmut Prendinger is a professor at the National Institute of Information processing, Tokyo, where he works in the Appendage Content and Media Sciences Research Division. He carries out research in the areas of 3D Internet, cyber social simulation, information analytics, virtual agents, intelligent multimodal interfaces, and emotion/position recognition from textual matter. He has publicized much 200 papers in peer-reviewed journals and conferences.

Watch full text