During the last decade, artificial intelligence (AI) and its applications have slowly but surely made their way into the financial services sector. Traditionally, those in financial services are resistant to change given the complexities in processes, security, and compliance as well as cost. However, the rise of Fintech companies has shown the industry the immense benefits of such innovations and provided some stern competition in the market.
One application of AI that has become increasingly popular and valuable is known as computer vision. In this article, we will look at what computer vision is, how it is being used, and why it is transforming financial services.
What is Computer Vision?
Computer Vision is sometimes abbreviated as CV and is the field of AI that aims to help computers understand the content of digital images like photographs and videos. In theory, the scope of the field is infinite given the dynamicity of the physical world. If you consider the number of things you see and perceive every day or even every minute, training a computer to do as a human would do is incredibly complex.
One of the most hyped examples of computer vision is autonomous vehicles. For a car to operate without a human driver, it will need to understand the entire environment around it. Can it recognize whether the object in front of it is a traffic light? Can it anticipate the car in front of slowing down? We are still a long way off from reaching this level of computer vision but industries like financial services are utilizing the technology in more simplified forms.
In its most basic applications, computer vision technology can recognize images, words, and patterns. Systems will be trained using huge amounts of unstructured data to a point where they can accurately predict the content of new information they are fed with. For a technical overview of computer vision, you can read this article from Towards Data Science which translates complex theory into an easily understandable summary.
Key Applications of Computer Vision in Financial Services
Financial Services institutions are typically hard ones to break into with innovation. However, the application of computer vision techniques is transforming and solving some longstanding problems amongst financial firms. These include cybersecurity, customer experience management, identification, and authentication of transactions.
In retail banking, there is a lot of scope for computer vision. Most of the buzz tends to come in the area of security and fraud. The use of biometrics and image recognition for authentication helps banks improve security and combat the potential of fraud.
CaxiaBank has gone one step further and allow customers to withdraw via ATMs using facial recognition. The ATM is able to validate up to 16,000 points on a facial image to fully verify the identification of the person making the withdrawal.
Know Your Customer (KYC) processes are also a large laborious part of retail banking. Computer vision can help banks with the process by matching customer pictures to adverse reports across the digital world.
BBVA uses computer vision to allow customers to submit a photo ID and a selfie. The platform then takes the information and uses computer vision to check that the images are the same. In banking, a lot of the processes associated with KYC are paper-based. Computer vision automates the manual work and improves accuracy, productivity, and efficiency within the bank.
Customer experiences can also be enhanced with computer vision. One example could be using images to recognize a customer as they walk into a branch meaning they receive the best possible service. Coupled with predictive analytics, they could even ascertain why the customer might be at the branch before they even speak to an advisor.
Other potential applications include checking facial expressions and emotions that analysis shows are signs of fraud, looking out for card skimming, and suspicious behaviors.
Document classification is a long arduous task within the commercial banking world. Computer vision has the capability to automate much of the process.
A tool like Amazon Rekognition can read unstructured documents at speed including images and videos. Traditional systems tend to struggle where financial documents come in various structures and templates. This means that document gathering, extraction, and processing can be automated. The speed at which the commercial bank completes activities is significantly increased as well as the accuracy levels of doing so.
The insurance industry is one that is primed for the use of computer vision. For example, in residential property, computer vision could accurately analyze images to investigate the condition of premises or home. This both negates the need for a physical inspection whilst automatically storing the data in case it is needed at a time of loss.
Computer vision may even be able to estimate the pay-out of claims at the time of loss. If loaded with enough images, as soon as a new claim is registered, there could, in theory, be an immediate pay-out if the computer vision platform can corroborate the information provided. One example could be with driverless vehicles. For autonomous cars to work, they will need to the constant video stream of the environment. This could be vital in analyzing claims going forwards.
Challenges of Implementing Computer Vision
With the opportunity to unlock cost savings and efficiencies, it is important that banking and financial service firms start to invest in computer vision. This does come with challenges around security and regulation like General Data Protection Regulation (GDPR) which can stifle innovation. It is important that institutions have well thought out strategies as to how they will counteract any such barriers.
Many banks and other financial services tend to work from legacy systems. It’s possible they will either need significant upgrades or work with modern Fintech companies to be able to effectively deploy computer vision platforms. This may be costly but at the same time vital in order to keep up with the competition.
Disclaimer: The author of this text, Robin Trehan, has an undergraduate degree in Economics, Masters in international business and finance, and MBA in electronic business. Trehan is Senior VP at Deltec International www.deltecbank.com. The views, thoughts, and opinions expressed in this text are solely the views of the author, and not necessarily reflecting the views of Deltec International Group, its subsidiaries, and/or employees.
Thank you for your interest in the Deltec Initiatives Foundation. You can contact us using the form below.
Before sending a message to us, kindly note that we do not accept requests for funding. Thank you for your understanding.