EU project to deliver forward-looking data

MILAN - A new way of obtaining operational risk data - over the web and in unstructured documents such as emails - is being developed by the EU.

Musing, or multi-industry, semantic-based next-generation business INtelliGence, is a EUR24 million four-year EU-funded research project that aims to integrate new semantic web and human language technologies to create tools that use structured and unstructured data with rule-based reasoning to gain better business intelligence.

Musing is investigating three industry virtualisations: financial risk management, internationalisation and IT operational risk. Op risk software and consultancy provider Ci3 is providing the real world input to the R&D project for the op risk virtualisation to ensure the results will have an application in the business world.

"The ultimate aim is that a risk manager could buy a system and explain to it the financial institution's view of risk," says Richard Pike, product director with software vendor Ci3 in Dublin. "The system then automatically goes throughout his bank looking at emails, fixed data and loss recordings, and then through the semantic web to build up an enterprise view of the current risk situation in the bank. The system then learns as new events occur and flags up new areas of concern or indicators, which the op risk manager can then action or mitigate."

The leading topics Musing is addressing are semantic-based knowledge management, ontology engineering, reasoning, Bayesian statistics, data mining, quali-quantitative data integration for an enterprise's assessment and self-assessment, next-generation rating systems, and multi-industry solutions and standards.

"The problem with the internet is that there is too much information out there. Although XML tagging of files makes it much easier to find relevant information, much of what is filed on the web - such as blogs and newspaper articles, does not get tagged," says Pike. "The semantic web is technology that, rather relying on the author to tag information, tells its computer system the areas it is interested in and sends that technology out onto the internet, which can then read unstructured data and understand which areas are relevant to what you are looking for. The semantic web does not yet exist - the idea of the research project is to see if it can get the semantic web to benefit business."

The semantic web is an evolving extension of the internet, in which web content can be expressed not only in natural language, but also in a form that can be read and used by software agents, permitting them to find, share and integrate information more easily. The idea is to use this technology to search the internet for relevant information - in this case operational risk loss data/events pertaining to an organisation's risk profile. Ontology engineering looks at how that data can be stored. An ontology describes the entities in a domain, such as operational risks, and the relationships they have with each other, including the reason for that relationship and the state of the relationship. Given all of this data, Bayesian engines can figure out the links between the data categories and find probabilities to help fill in any gaps in the data, allowing op risk managers to better target areas of operational risk. The FSA is keen on correlation and interdependency of risks, but trying to get financial organisation to do this is very difficult at the moment.

"Bayesian networks can aid the integration of qualitative and quantitative data," says Pike. "For example, if I don't have any root-cause data, I can make a qualitative assessment and manually type that into the Bayesian network. The aim of Musing is to effectively build the next generation of risk-weighting systems through this mix of qualitative and quantitative integration."

Using this type of intelligent network will allow op risk managers to identify areas of risk and to be able to profile which mitigation solutions would be most effective and most cost-effective for the organisation. Ci3 is piloting this with its clients at the moment.

"We only expect to get 50% of this stuff to work by 2010 as it is so far advanced," says Pike. "The idea with this research project is to really push the envelope. But, that said, we are already seeing real benefits by using individual aspects of the research such as the Bayesian networks to deliver to our clients. We are now looking at doing the same thing with scenarios with real industry data. This involves breaking down the causes of the scenarios into small pieces and assessing the risk of those, then using the Bayesian map to sort out all of the linkages between them, which would profile the true risk of the scenario."

Other members of Musing are Innsbruck University in Austria, European Business Register from Belgium, the German Research Centre for Artificial Intelligence, KPA and Tadiran Telecom Communication Services in Israel, French company Metaware, Pavia University, Banca Monte Pasci Di Siena and Pisa University in Italy, and Creditreform and Sheffield University in the UK.

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact info@risk.net or view our subscription options here: http://subscriptions.risk.net/subscribe

You are currently unable to copy this content. Please contact info@risk.net to find out more.

Financial crime and compliance50 2024

The detailed analysis for the Financial crime and compliance50 considers firms’ technological advances and strategic direction to provide a complete view of how market leaders are driving transformation in this sector

Investment banks: the future of risk control

This Risk.net survey report explores the current state of risk controls in investment banks, the challenges of effective engagement across the three lines of defence, and the opportunity to develop a more dynamic approach to first-line risk control

Op risk outlook 2022: the legal perspective

Christoph Kurth, partner of the global financial institutions leadership team at Baker McKenzie, discusses the key themes emerging from Risk.net’s Top 10 op risks 2022 survey and how financial firms can better manage and mitigate the impact of…

Emerging trends in op risk

Karen Man, partner and member of the global financial institutions leadership team at Baker McKenzie, discusses emerging op risks in the wake of the Covid‑19 pandemic, a rise in cyber attacks, concerns around conduct and culture, and the complexities of…

Moving targets: the new rules of conduct risk

How are capital markets firms adapting their approaches to monitoring and managing conduct risk following the Covid‑19 pandemic? In a Risk.net webinar in association with NICE Actimize, the panel discusses changing regulatory requirements, the essentials…

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here