Financial technology (Fintech) has mainly developed over the last ten years. Since its birth somewhere just over a decade ago, the term has become a household name thanks to the massive investments into companies surrounding it. By the end of 2020 new Fintech investments are set to hit $30 billion from $1.8 billion back in 2011.

The key reason for the growth has been the focus on innovative artificial intelligence (AI) solutions that have been able to disrupt the financial services sector. Whilst traditional banks the use of legacy systems have struggled to keep up with customer demand in a digital ecosystem, Fintech companies have been able to flourish with their agility and technological expertise.

AI is the heartbeat of most Fintech firms. The ability of AI platforms to solve human problems, reduce costs, and enhance efficiency makes it a must-have asset. Fintech’s are using AI at every stage of their journey to offer high-quality service and expert customer journeys.

One application of AI that has been particularly successful for Fintech firms is known as computer vision. In this post, we will look at what computer vision is and how Fintech firms are using it to their advantage.

What is computer vision?

Computer vision is an application of AI that started as far back as the 1950s. The technology allows computers to see a view of the world, turn it into data, and make decisions from how it understands the analysis. It can be thought of as similar to the way humans might look at the world. Advances in computing power have meant that machines are faster than humans at recognizing visual cues which is why we are beginning to see accelerated developments in new technology like driverless cars.

Computer vision works by being trained with thousands or millions of images and videos (or any unstructured data types for that matter). When it sees a new image or video, it can interpret the data points and accurately depict what it sees.

Driverless cars like Audi will use a number of sensors to understand other road users and traffic signals or signs.

Computer vision in Fintech

There are numerous ways that Fintech companies are using computer vision as part of their offering.

Know Your Customer (KYC)

BBVA bank is using computer vision as a way of carrying out their KYC processes which are used for customer identification. Customers are able to open their accounts using either a selfie or via a video call rather than the traditional weeks of verification checks.

With a process like this, the banks are able to reduce human effort whilst providing customers with a journey that they can complete from the comfort of their own home.

Digital Codes

Wells Fargo is using machine vision to create a cardless ATM process. Instead of using a debit card when visiting an ATM, customers are given a one-time use digital code which is accessed from a smartphone.

As customers do not need to have cards, the risk of fraud is heavily reduced via identity theft. With Google and Apple already developing their own payment systems, along with the rise of cryptocurrency, it seems only a matter of time before we don’t need to rely on physical cash.

Home Insurance

Efficient underwriting is critical to home insurance. This means that customers should be charged a premium that is fitting to their property. For example, older properties will demand a higher premium as they are seen as a greater risk to the insurer.

Fintech companies like Cape Analytics are using computer vision to analyze satellite imagery and see the aerial view of properties. Insurers are able to use the data to view valuable property attributes at the time of underwriting. This will analyze the condition of the roof for example which could easily go unnoticed otherwise and lead to large claims.

Assisting hedge funds

In a similar sector to Cape Analytics, Orbital Insight specialize in geospatial analytics. An example they provide is where their platform could track the number of cars in Walmart parking lots. They will then look at the historic imagery and economic trends to train models and forecast results. The imagery will be turned into valuable insight for Fortune 500 and hedge fund companies.

Document Extraction

Financial service institutions handle a lot of documentation. If they need to find the information contained in one of those documents, it can take a significant amount of time and labor cost. Fintech companies such as Hyperscience have created computer vision platforms that automate document extraction. The data from vast numbers of incoming documents will be automatically analyzed.

Computer vision algorithms can understand the documents and submit them to the right area for review. It is even able to do this with tough to read handwritten text.

A recent article about the start-ups Signzy claims that their computer vision engine can process as many as 3.5 million documents per day for banks. The potential for reviewing transactions and verification forms to reduce risk is huge for the banking sector. This is one document every 0.09 seconds which takes a human 20 minutes.

Damage Evaluation

A challenge for insurance companies is finding the time and resources to assess the damage, whether it be a home, car, or possession. Using computer vision, they can have a process whereby a scanned image is automatically analyzed, compared to the insurance cover of the customer and an appropriate decision is made. For example, if a customer sends a photo of a damaged iPhone, the data points can be compared to their cover to check if they have the necessary insurance, paying the claim instantly.

Summary

The ideas in this post only scratch the surface as to how computer vision could be used to shape financial services. In the forthcoming decade, there will without a doubt be new developments as processing speeds improve and algorithms become more complex. There is a high possibility that we are here in ten years without any physical currency or at least a very limited amount. Fraud will be irrefutable with the identity verification techniques that computer vision makes available.

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 deltecbankstag.wpengine.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.