You are here:  Home  >  Uncategorized  >  Current Article

Consuming XBRL Financial Information: Semantic Web Prototype App Aims To Make It Easier, Faster, Automatic — And Socially Connected

By   /  July 14, 2010  /  No Comments

stockex.jpg There’s no replacement for XBRL. But Dr. Graham G. Rong, Fellow at the MIT Sloan School of Management and chair of the MIT Sloan CIO Symposium, thinks there are opportunities for Semantic Web technologies to enhance it, turning the data within financial reports into meaningful knowledge that helps both the producers and consumers of these materials.

Rong is working on a software prototype for translating financial reports from the XBRL format into the OWL language, the idea being to preserve and enhance the implicit semantics in XBRL and enable the logic model of financial reports, according to a soon-to-be-published paper co-authored by Rong.

Such a translation, the paper argues, reduces the risk of redundancy and inconsistency, and enables the quick and useful inference on XBRL-based financial information for business decisions. “This is a significant advancement in the better consumption of XBRL-based financial filing mandated and supported by the SEC,” Rong says. “The XBRL specification itself, led by XBRL International and accepted by accounting, financial, regulatory and corporate communities, is a great achievement.”

The prototype, hailing from Rong’s temporary brand, International Data Automation, seeks to build off the synergies between XBRL and the Semantic Web, Rong says – machine readability, automation, easier communications between parties in a value chain, and an XML heritage. “The difference is that XBRL is really data-based to represent data. It is a data model, not a knowledge model. But Semantic Web – e.g. OWL or RDF — represents knowledge. That’s a huge difference,” Rong says. “If you summarize it in a broad way, with Semantic Web-based information you can apply all the AI facilities on top of that data, reasoning, inferencing, all those things which with XBRL alone are not easy to do.”

xbrlgrahampix.png As examples, Rong describes how logical models enable the definition of equivalency relations and child-parent relationships, in both directions, in one step, whereas these have to be defined in both directions in XBRL to avoid both redundancies and the risks of data inconsistency. For information consumers’ advantage, incorporating the logical model into the digital financial report could automate validation checks — for example, that total assets by geography and total assets by product line (as shown in the image at left) are the equal of each other, and should present the same result.

“Anyone can get the information [from the online SEC XBRL filings] and read it, but how to make good use of it is another thing,” Rong says. Today a lot of money is spent on services from companies like Bloomberg and Thomson Reuters to help them summarize and understand the data. “What we do as a business is to make the consumption of the XBRL based digital financial information easier, faster and automatic. That’s the fundamental idea or value.”

Another issue the prototype seeks to address is using semantic web technology to incorporate social and financial analytics. On top of the XBRL information in financial documents, the software uses semantic web technologies (linked data) to understand affiliated information on the Internet about a company, its ecosystem of partners, suppliers and customers, and its competitors, too, as well as current events.

“This information can be in any format of structured or unstructured information, like newspaper articles, press releases, Tweet messages, Facebook messages or DBpdia ….So we can find that relevant information, and combine that with financial data from the SEC to provide a more complete, in-depth and automated financial analytics.” The enhancement and usage of “semantic richness” has become a trend in light of the adoption of the semantic web structure by Yahoo!, Google and more recently by Wikipedia, Twitter and Facebook, he says.

grahamphoto.png Not to mention that it should lead to more timely analysis, as well, given that public companies submit XBRL data to the SEC only once every three months. “What happens during those three months is important and that information is widely distributed on the Internet,” Rong says. “How to combine that widely distributed information scattered anywhere with financial data — that is one of the core functions of the system we develop.”

Rong says the prototype will offer comprehensive and advanced visualization features to make the information more accessible, and even sees a way companies themselves can use it internally for supporting governance, risk and compliance (GRC) requirements.

Photo: Courtesy Flickr/Rob Young

• Don’t forget to propose your startup for our Semantic Web Impact Awards. The deadline is Sept. 15.

About the author

Jennifer Zaino is a New York-based freelance writer specializing in business and technology journalism. She has been an executive editor at leading technology publications, including InformationWeek, where she spearheaded an award-winning news section, and Network Computing, where she helped develop online content strategies including review exclusives and analyst reports. Her freelance credentials include being a regular contributor of original content to The Semantic Web Blog; acting as a contributing writer to RFID Journal; and serving as executive editor at the Smart Architect Smart Enterprise Exchange group. Her work also has appeared in publications and on web sites including EdTech (K-12 and Higher Ed), Ingram Micro Channel Advisor, The CMO Site, and Federal Computer Week.

You might also like...

AWS Announces Five New Machine Learning Services Including SageMaker, DeepLens

Read More →