Category: news

Earlier this week Insurance Edge ran a news story about the amount of insurance fraud which takes place daily across the UK. Although some types of fraud are in decline, there are always new scams and swindles being tried. Can Artificial Intelligence help? Well, David Fulton CEO of WeSee, thinks that we can tackle insurance fraud once and for all with emotion recognition.

One insurance scam is detected every minute in the UK; that’s according to new research published by the Association of British Insurers (ABI). A total of 562,000 insurance frauds were found out by insurers in 2017, of which 113,000 were fraudulent claims and 449,000 dishonest insurance applications.

But what if you could simply interview a claimant and instantly be able to assess the probability of them telling the truth? What if you could assess claimants’ facial expressions for suspicious signals, simply by interviewing the claimant using a smartphone camera?

Forget the ‘what ifs’, the truth is that this technology exists today and it could just be the insurance industry’s saviour – facial and emotion recognition technology that understands every multi-layered element within images and videos in the same way humans do. While it’s fair to say that the industry is making strides in detecting and deterring fraud through collaborative work, with the number of fraud crimes down by 8% compared to 2016, the ABI still puts the value of fraudulent claims at £1.3bn (up slightly by 1%).

The answer is quite simple really. Using advanced deep learning techniques, there is a system out there that can analyse an individual’s responses and micro-emotion reactions to a set of questions in real time and deliver an assessment of their veracity to the insurer almost instantly, feeding back visual data and cues to an AI-driven intelligent computer system. What’s more, this would be in the form of a visual dashboard delivering key guidance to the claims handler, enabling them to do their job more effectively by flagging up clearly the most suspicious claimants for further, more detailed investigation.

It has the ability to detect emotions – or more specifically suspicious behaviour – in real time through monitoring and analysing micro-expressions, eye movement, gaze, speech patterns and tone of voice, along with identifying seven key human emotions.

Applied to claimants, it has the power to transform the way insurance companies process claims, assessing their validity more scientifically and accurately than ever before. As the latest ABI figures highlight, the insurance industry needs to reduce the huge burden of fraudulent claims that is currently draining profits. Equipping insurance claims handlers with the tools and technology they need to do their job more effectively by flagging up clearly the most suspicious claimants has the power to benefit the insurance industry, saving time and money for everyone, and combating insurance fraud once and for all.

Original source: https://insurance-edge.net/2018/08/25/opinion-emotion-recognition-could-eliminate-insurance-fraud/

Enjoy the full interview here:

https://noticias.r7.com/fala-brasil/videos/cameras-de-reconhecimento-facial-ja-sao-capazes-de-ler-as-emocoes-das-pessoas-03082018

By now, most of us are familiar with Artificial Intelligence (AI), the software that powers many of our latest gadgets and devices day-to-day.

From the digital personal assistants we rely on like Amazon Echo to the experiences in video games, AI is a integral part of everyday life to many of us.

However, could it be better used to solve a more serious problem? In our world, insurance fraud is a big issue.

There are some existing tools that can be used to combat it. One is the Insurance Fraud Register, which holds details of individuals who have been associated with fraudulent activity in the past. However, it only has data going back to 2013, so there is room for error.

What’s more, just 62% of general insurers use the system, meaning a large number of criminals can potentially slip through the net. It’s an expensive problem: research from the Association of British Insurers (ABI) shows that in 2016 there were around 125,000 fraudulent claims amounting to £1.3 billion.

The research also suggests that a similar amount of frauds go undetected every year. Car insurance scams like “crash for cash” frauds are commonplace. Detecting just 1% of these claims could save the industry £13 million.

But an AI-led solution could be just around the corner.

AI company WeSee is developing a system that can analyse involuntary vocal and facial responses including pupil dilation, tone of voice and eye movement, to detect dishonest or suspicious behaviours.

David Fulton, CEO of WeSee, said: “Using advanced deep learning techniques, the system would analyse an individual’s responses and micro-emotion reactions to a set of questions in real time and deliver an assessment of their veracity to the insurer almost instantly.”

Detecting just 1% of these claims could save the industry £13 million.

He says this will help insurance claims handlers “do their job more effectively by flagging up clearly the most suspicious claimants for further, more detailed investigation.”

Technological developments like this can benefit the insurance industry and our customers tremendously, potentially reducing costs by saving time and money for everyone and catching more of those who try to commit insurance fraud.

Original source: https://www.dlgdigital.co.uk/news/is-ai-shaping-the-future-of-insurance-fraud-investigations

Facial recognition tech is becoming more sophisticated, with some firms claiming it can even read our emotions and detect suspicious behaviour. But what implications does this have for privacy and civil liberties?

UK firm WeSee, for example, claims its AI tech can actually spot suspicious behaviour by reading facial cues imperceptible to the untrained eye.

Emotions, such as doubt and anger, might be hidden under the surface in contrast to the language a person is using.

WeSee says it has been working with a “high profile” organisation in law enforcement to analyse people who are being interviewed.

“Using only low-quality video footage, our technology has the ability to determine an individual’s state of mind or intent through their facial expressions, posture, gestures and movement,” chief executive David Fulton tells the BBC.

“In future, video cameras on a tube station platform could use our tech to detect suspicious behaviour and alert authorities to a potential terrorist threat.”

“The same could be done with crowds at events like football matches or political rallies.”

 

Read the full article here:

https://www.bbc.co.uk/news/business-44799239

In the quest for a safer world, it looks increasingly like artificial intelligence will play a leading role. Facial recognition has proved to be the most prevalent security application to date, with the technology being used to check identities at the airport, along with a number of other emerging uses.

In business, for example, it has been brought in to verify boardroom members. In terms of law enforcement, Berlin is currently trialing facial recognition cameras to spot known terrorists. Meanwhile, the Chinese city of Xinjiang has taken things a step further by arming its police officers with Google Glass-like headsets equipped with facial recognition scanners to help them to identify criminals.

The technology looks set to drag security and policing into the 21st century, and if handled responsibly can make our cities safer places for our children and future generations. However, facial recognition is just the start. Pioneers in computer vision are continually innovating, looking beyond basic identification applications towards developing more sophisticated technology that can determine emotions and more.

The latest emotion recognition technology understands every multi-layered element within images and videos in the same way humans do. This allows it to recognize and analyze images and faces in video content with up to 98 percent accuracy – and up to 1,000 times faster than the human brain.

Harnessing the power of deep learning and neural networks, it can detect suspicious behavior in real time through monitoring and analyzing pupil dilation, eye movement, gaze, micro-expressions, speech patterns and tone of voice, along with identifying seven key human emotions.

One of the first applications of this technology looks set to be in reducing insurance claims fraud, which costs the UK alone £1.3 billion, according to research by the Association of British Insurers. By monitoring a video of a claimant answering questions at point of an application or claim, the technology will be able to give them a rating providing claims experts with an indication of the likelihood of them telling the truth, or not.

The potential of emotion recognition is already exciting security companies and law enforcement agencies across the globe, due to its ability to determine an individual’s state of mind or intent through their facial expressions, posture, gestures and movement. The fact that this can be done from different angles, and even if the subject is moving or partially obscured, say by a balaclava, as well as under various light conditions is particularly impressive. Dangerous objects can also be detected.

Video cameras on a tube station platform, for example, could detect suspicious behavior and alert police to a potential terrorist threat. The same could be done with crowds at events like football matches. Nervousness and anxiety shown by someone using a cash point could be an indication that they are using a stolen cash card, triggering the machine to stop the requested transaction or alert the police.

More effective law enforcement and security in terms of better detection and prevention rather than increasing personnel and firepower will make for a safer society both on the streets and in the workplace. Put simply, emotion recognition technology will make it easier to look after the good guys and help to catch the bad. Furthermore, spreading the word about what can be achieved across society should act as a great crime deterrent. Although governments can’t guarantee a brighter future, they can deliver a safer one.

Original source: https://securitytoday.com/Articles/2018/06/19/How-AI-Can-Deliver-a-Safer-Future.aspx?Page=1

We’re hearing about more and more applications of AI-driven facial recognition systems, from checking identities at the airport to verifying board members for meetings. Taking things a step further, The Times reported recently that the Chinese city of Xinjiang has given its law enforcement officers Google Glass-like headsets equipped with facial recognition scanners to help them to identify criminals. Meanwhile, Berlin is testing terrorist-spotting facial recognition cameras.

Beyond security, the latest uses of facial recognition include scanning unborn babies to diagnose rare diseases and common genetic disorders. It’s also helping reduce traffic accidents by spotting driver fatigue and prosecute jaywalkers.

But that is just the tip of the computer vision iceberg. Current applications are using AI to identify individuals, but it’s possible to take the technology a lot further. Trials are going on right now that are applying deep learning to recognising human emotions. This major leap in facial recognition is driven by technology that understands every multi-layered element within images and videos in the same way humans do, allowing it to analyse and recognise images and faces in video content with up to 98% accuracy – and 1,000 times faster than the human brain. Such visual intelligence also means it can monitor facial micro-expressions, analysing pupil dilation, eye movement and gaze. By combining this with speech pattern and tone of voice analysis, it can identify seven key human emotions – Anger, Contempt, Fear, Disgust, Happiness, Sadness and Surprise.

By simply scanning someone’s face live or on video, in real time, it can not only identify a person but also assess their emotional state more deeply than any human can. Rather than simply spotting whether someone is happy or sad, it can gauge integrity – essentially, whether someone is telling the truth or not. Or rather the likelihood that they could be lying. This takes facial recognition to a whole new level in terms of deceit detection. The potential of such a level of sophistication, with the emotional nuances it can identify, has clear implications for law enforcement and the ability, if responsibly managed, to create a safer society, looking out for the good guys and catching the bad. In fact, it should cut crime through deterrent alone.

However, the technology also has lots of potential applications outside of crime that could actually transform business. Take insurance, for example. Fraudulent claims are costing the sector dearly. Last year, some 125,000 claims were detected in the UK alone worth £1.3 billion, according to research by the Association of British Insurers. Moreover, it is estimated that a similar amount of fraud goes undetected each year. Hence it’s no surprise that insurers in the UK, which boasts the fourth largest underwriter community in the world, invest at least £200 million annually to identify fraudsters.

The latest computer vision technology applied to insurance claimants will be a vital additional node of information for insurers in their fight to reduce fraud, with the power to transform the way claims are processed by assessing their validity more scientifically and accurately than ever before. During a live video interview, for example, it could provide claims assessors with a ranking in terms of the likelihood that a claimant is being truthful. The figure would give an indication of whether the claim should be investigated further. As well as helping detect fraudsters, it could also be used to reward integrity through lower premiums.

The fact is you simply can’t put a price on integrity. Well, actually in insurance terms you might say you could, as being able to detect it could be worth billions! The thing is integrity is important in all walks of life and business. Doesn’t every company want to employ people with integrity? Being able to gauge it could not only improve recruitment success, but also, as a direct result, business performance. And of course we’re just scratching the surface here. Soon it might be possible to use computer vision to detect nuances of personality that could take over from biometric testing. And who knows where we could go from there?

The fledgling elements of this technology are here right now. All innovation has its potential upsides and downsides. Used responsibly, computer vision has the potential to transform our personal and professional lives for the better.

Insurance fraud is big business. Last year, some 125,000 claims were detected in the UK, worth £1.3 billion, according to research by the Association of British Insurers. But could a new generation of AI (Artificial Intelligence) powered face and behaviour analysis software apps help detect fraudulent claims?

One company, We See, thinks so and says that the next steps in AI technology development spells good news for insurers. That’s because it will take facial recognition to a new level by being able to detect suspicious behaviour in real time through monitoring and analysing pupil dilation, eye movement, gaze, speech patterns and tone of voice, along with identifying seven key human emotions. A bit like the scenes in the sci-fi classic Blade Runner, where a test is applied to detect humans from robots.

Applied to claimants, it has the power to transform the way insurance companies help process claims and assess their validity more scientifically and accurately than ever before.

The system is currently being developed for insurance companies to assess claimants’ facial expressions for suspicious signals. The claims handler would simply interview the claimant using their smartphone camera, which would be feeding back visual data and cues to an AI-driven intelligent computer system.

Using advanced deep learning techniques, the system would analyse an individual’s responses and micro-emotion reactions to a set of questions in real time and deliver an assessment of their veracity to the insurer almost instantly. This would be in the form of a visual dashboard delivering key guidance to the claims handler, enabling them to do their job more effectively by flagging up clearly the most suspicious claimants for further, more detailed investigation.

In a lighthearted test, early versions of the system were used to assess just how convincing Jeremy Corbyn’s and Theresa May’s speeches were during this year’s General Election with strong results – which remain behind closed doors, according to We See.

In 2018, insurers will get the chance to use the technology on bona fide claimants to help reduce the huge burden of fraudulent claims that is currently draining insurance company profits.

A new system based on deep learning technology could save the insurance industry billions in fraudulent claims, says David Fulton, CEO at WeSee

Fraudulent claims are costing the global insurance sector dearly. Last year, some 125,000 false claims – worth £1.3 billion – were detected in the UK alone, according to research by the Association of British Insurers. Moreover, it is estimated that a similar amount of fraud goes undetected each year. So it’s no surprise that insurers in the UK, which boasts the fourth-largest underwriter community in the world, invest at least £200 million annually to identify fraudsters. Looking globally, the getmeIns USA Focus predicts that detecting just one per cent of fraudulent claims would save companies in the leading 10 insurance nations $35 billion collectively. This has made the quest for a solution of paramount importance to insurers. Up until now, they have remained disappointed – but sophisticated artifi cial intelligence (AI) driven by deep learning could be their saviour. Huge strides have been made recently in terms of image and facial recognition. This new technology understands every multi-layered element within images and videos in the same way humans do. This allows it to analyse and recognise images and faces in video content with up to 98-per-cent accuracy – and 1,000 times faster than the human brain. In its current form, this advanced AI technology is helping broadcasters to identify key people and objects in video footage to streamline the editing process. Media data science company Genistat used the technology during this year’s European Open Golf Tournament to detect leading golfers and sponsor logos quickly and accurately across hours of footage, significantly speeding up the creation of highlight clips. Make way for the future However, it is the next step in this technology’s development that spells good news for insurers. Soon, facial recognition will be able to detect suspicious behaviour in real time through monitoring and analysing pupil dilation, eye movement, gaze, speech patterns and tone of voice, along with identifying seven key human emotions. Applied to claimants, it has the power to transform the way insurance companies help process claims and assess their validity more scientifically and accurately than ever before. Imagine you could simply interview a claimant and instantly be able to assess the probability of them telling the truth. Well, this is no longer the stuff of insurers’ dreams or fraudulent claimants’ nightmares.

 

The system currently being developed for insurance companies assesses claimants’ facial expressions for suspicious signals. The claims handler would simply interview the claimant using their smartphone camera, which would be feeding back visual data and cues to an AI-driven intelligent computer system. Using advanced deep learning techniques, the system would analyse an individual’s responses and microemotion reactions to a set of questions in real time and deliver an assessment of their veracity to the insurer almost instantly. This would be in the form of a visual dashboard delivering key guidance to the claims handler, enabling them to do their job more effectively by flagging up clearly the most suspicious claimants for further, more detailed investigation. In a lighthearted test, early versions of the system were used to assess just how convincing UK Leader of the Opposition Jeremy Corbyn and Prime Minister Theresa May’s speeches were during this year’s General Election, with strong results – which remain behind closed doors! In 2018, insurers will get the chance to use the technology on bonafide claimants to help reduce the huge burden of fraudulent claims that is currently draining insurance company profits – and it looks set to transform the industry.

 

WeSee, the deep learning-based computer vision innovator that can detect suspicious behaviour, has been selected to participate in Pitch@Palace 9.0, the initiative founded by The Duke of York in 2014 as a platform to amplify and accelerate the work of Entrepreneurs. WeSee will compete at Pitch@Palace Boot Camp on 13 March at the University of Manchester, ahead of Pitch@Palace 9.0 at St. James’s Palace on 25 April.

Pitch@Palace was established to guide and support Entrepreneurs in the development of their business ideas. The theme for Pitch@Palace 9.0 is ‘Data, Intelligence and the Future of Security’ and will showcase companies that have developed innovative technologies to solve prevalent security issues that businesses and individuals are exposed to today.

WeSee was selected from among hundreds of applicants to take part in Pitch@Palace 9.0 and attend Boot Camp in Manchester. Powered by deep learning and neural networks, WeSee uses deep learning-based computer vision; it is able to detect objects, logos and faces in images, and read, detect and categorise video / live content in real-time.

The potential benefits to insurers, looking to authenticate claims as quickly, accurately and promptly as possible, is huge. Many insurers and brokers already used voice analysis software to detect fraud, so applications like WeSee take that process to the next step. It could also make analysis of dashcam footage a less labour intensive, more automated process.

Its latest innovation now takes that a step further; WeSee’s Neural Network embedded inside iPhone or device, can detect emotions, micro expressions and many advanced facial clues to detect emotional sentiment, micro-reactions that are invisible to the naked eye, highlighting positive, and or, suspicious behaviour; offering something invaluable particularly to the security, recruitment and insurance sectors.

David Fulton, CEO of WeSee, said: “It’s an absolute privilege for WeSee to be selected for Pitch@Palace9.0 – it’s an incredible event and amazing connections are being made. We see our visual intelligence as a cornerstone to future security and deceit detection efforts.”

Pitch@Palace Boot Camp provides Entrepreneurs with the chance to hear from leading industry experts and Pitch@Palace Alumni, as well as receiving support and mentoring. All are asked to Pitch their business to a panel of Judges, as well as senior business leaders, investors, and influencers from across the technology, investment and business communities. The Judges will select 12 Entrepreneurs to Pitch for three minutes at Pitch@Palace 9.0 at St. James’s Palace on 25 April. The rest of the Entrepreneurs will have the opportunity to Pitch for 30 seconds at the final event.

 At St. James’s Palace, the Pitch@Palace 9.0 Winner and Runners Up will be selected from among the 42 companies, by the Audience vote. All 42 Entrepreneurs will also take part in the Pitch@Palace People’s Choice Award, which opens on 13 March. The Pitch@Palace People’s Choice Award Winner will also be named on 25 April, as voted for by the public.