Big Data Algorithmic Trading Systems Based on Investors’ Mood

Raúl Gómez Martínez, Miguel Prado Román and Paola Plaza Casado

Journal of Behavioral Finance, 2019, vol. 20, issue 2, 227-238

Abstract: Traditional automated trading systems use rules and filters based on Chartism to send orders to the market, aiming to beat the market and obtain positive returns in bullish or bearish contexts. However, these systems do not consider the investors’ mood that many studies have demonstrated its effects over the evolution of financial markets. The authors describe 2 "big data" algorithmic trading systems over Ibex 35 future. These systems send orders to the market to open long or short positions, based on an artificial intelligence model that uses investors’ mood. To measure the investors' mood, the authors use semantic analysis algorithms that qualify as good, bad, or neutral any communication related to Ibex 35 made on social media (Twitter) or news media. After 1.5 years of research, conclusions are: First, the authors observe positive returns, demonstrating that investors’ mood has predictive capacity on the evolution of the Ibex 35. Second, these systems have beaten the Ibex 35 index, showing the imperfect efficiency of the financial markets. Third, big data algorithmic trading systems numbers are better in Sharpe ratio, success rate, and profit factor than traditional trading systems on the Ibex 35, listed in the Trading Motion platform.

Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://hdl.handle.net/10.1080/15427560.2018.1506786 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:hbhfxx:v:20:y:2019:i:2:p:227-238

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/hbhf20

DOI: 10.1080/15427560.2018.1506786

Access Statistics for this article

Journal of Behavioral Finance is currently edited by Brian Bruce

More articles in Journal of Behavioral Finance from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().