"The intelligence of Fujitsu’s approach is evident in the remarkably high success rate. Fifty-seven per cent of the data returned was genuine and that has enabled us to bring in significant funds which we can redeploy across the council."
Mike Pinder Head of Anti-Fraud and Internal Audit, Southwark Council
Southwark Council is a borough in south east London, directly south of the River Thames and the City of London. Formed in 1965, it has a population of roughly 288,000 and is home to some of London’s most iconic buildings including Europe’s tallest building The Shard, London Bridge, Shakespeare’s Globe and the Tate Modern Museum. It also hosts numerous educational establishments including London South Bank University, which has over 23,000 students.
The borough has a significant student population with approximately 2,400 properties occupied by students and over 5,000 individuals claiming exemption from Council Tax. As is the case in any other UK council, these students are exempt from Council Tax. However, verifying claims for exemption is difficult. The council, in a bid to make savings, wanted to find a cost-effective way of identifying fraudulent claims.
“Research indicates that student Council Tax is one of the main areas where councils are exposed to fraud so naturally we want to combat this to ensure people pay what they owe,” explains Mike Pinder, Head of Anti-Fraud and Internal Audit, Southwark Council. “However, it is easier said than done. London has a massive student population and many educational institutions so verifying who is studying what, where and for how long is a real challenge.”
As it happened Her Majesty’s Revenue & Customs (HMRC), a non-ministerial department of the British Government responsible for the collection of taxes, was already looking at similar issues at a national level. It had partnered with Fujitsu to introduce automated processes for identifying fraudulent claims using predictive regression models to assess risk for all new tax credit claims. To increase the accuracy of fraud prediction, it also incorporated lifestyle data into the models.
“HMRC and the National Fraud Authority introduced us to Fujitsu and the pilot they were working on together. We realised this could help us easily and quickly identify questionable claims for exemption,” adds Pinder. “However, as it stood, the Fujitsu solution did not incorporate information on education status. We provided this data and asked Fujitsu to tailor the analysis to our needs.”
Fujitsu’s solution establishes a fraud screen which can identify the claims that are most likely to be fraudulent or erroneous. The system automatically correlates known facts about each individual such as the distance between their home postcode and the university; the length and subject of the course being studied, as well as other available lifestyle data. The fraud screen then streams the data through an analytics processing engine and a range of analytic algorithms to help predict which claims are bogus.
“If you live in Southwark and claim student exemption but the data shows you study at Edinburgh or Leeds, this raises a red flag because of the huge distance involved,” continues Pinder. “Likewise, if you claim to be a student but also hold a company directorship – it is simply not a probable scenario.”
Southwark Council provided Fujitsu with a list of 5,000 people who were receiving student exemptions. By running them through the system, Fujitsu identified 750 high risk matches where the status of individual claimants was unclear.
“We needed to populate the list of suppliers and educational institutions, and then sent it to Fujitsu who worked its magic and returned 750 questionable claims,” comments Pinder. “The next step then was for us to contact these people and establish the truth of the situation.”
As a result, Southwark Council was able to correctly identify 423 claimants who were no longer students – a hit rate of 57 per cent. By bringing these citizens back onto the Council Tax register, the council was able to generate an additional £500k in revenue.
“The intelligence of Fujitsu’s approach is evident in the remarkably high success rate. Using other methods, we might expect to only have ten per cent accuracy which necessitates much more work,” says Pinder. “In this case, most of the data returned was genuine and that has enabled us to bring in significant funds which we can redeploy across the council.”
Stephen Harrison, Chief Executive Officer, National Fraud Authority, concludes:
“As part of the development of our local government strategy ‘Fighting Fraud Locally’ we have worked closely with councils, including Southwark, to pilot a scheme to root out Council Tax evaders. Fraud is not a victimless crime and as a result of this pilot Southwark Council has identified additional income. Other councils could learn a lot from this pilot.”
Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Over 170,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenues of 4.5 trillion yen (US$54 billion) for the fiscal year ended March 31, 2012. For more information,, please see www.fujitsu.com
Case Study - Southwark Council (252 KB/A4, 2 pages)
Deel deze pagina via