Project First, the European Union-backed research effort to find a way of extracting and analysing financial services-related sentiment from social media networks, has concluded with the launch of a prototype market surveillance system.
Launched in late 2010, the three year project aimed to harness artificial intelligence to find information on the Internet that can then be used to support financial decision makers.
It was overseen by a consortium including Banca Monte dei Paschi di Siena, Boerse Stuttgart, Interactive Data b-next and the University of Hohenheim, with the aid of a EUR4.6 million budget co-funded by the EU.
The findings show how the sentiment reflected in social media postings can be automatically analysed and summarised to form an indicator. This source of information increases the probability that financial market trends can be correctly anticipated, says Christoph Lammersdorf, CEO of the Management Board of Boerse Stuttgart.
"Such tools could also help private investors making investment decisions to factor in social media content more efficiently," he says. "As an exchange organisation for the retail business, we see it as our job to support research into innovative technologies for private investors."
Ulli Spankowski, who led the project for Boerse Stuttgart and Stuttgart Financial, highlights another area of application: "The software developed for the First project also enables early detection of manipulative behaviour on the part of individual market participants. That opens up new opportunities for trading surveillance offices and other regulatory authorities."
Existing state-of-the art market-surveillance solutions do not yet take into account unstructured data.
"The developed prototype thus can make a major contribution to better detect market abuse and offers groundbreaking possibilities to increase the efficiency of market supervision and financial market regulation," says b-next, which already offers a suite of compliance and market surveillance software.