Credit reference agency Experian knows a lot about our money. The company has gathered approximately 3.6 petabytes of data on individuals all around the world, with data coming from marketing databases, transactional records and public information such as court records. That’s why banks and financial institutions turn to Experian to help them decide whether to lend to a mortgage applicant.
As in all areas of financial services, the way Experian works is being rapidly transformed by the technological advances being seen throughout the industry – and big data, artificial intelligence and machine learning is at the sharp end of this innovation.
How Experian uses Big Data in practice
Experian CIO Barry Libenson told me how Experian – itself a frontrunner in data and analytics – is adapting its business in line with the challenges and rewards brought about by cognitive (i.e. self-teaching) computers. “Machine learning is absolutely one of the hottest topics right now and something we are embedding into our products, in terms of better decisions and analytics,” says Libenson.
One use of machine learning that’s exciting people in the financial industry is the possibility of making the lengthy, labour-intensive process of applying for a mortgage a whole lot quicker and easier.
In much of the developed world, the way we apply for mortgages has hardly changed over the last few decades. As Libenson explains, “I’ve applied for several mortgages over the years and the only thing that’s different today from how it was 30 years ago is that I’m able to complete about 80 percent of the process using digital signatures instead of having to sign massive stacks of paper. At the end of the day, though, in order to get that cheque and get the money deposited, I still have to go to a title office and sign 50 documents so the money can be wired to the property owner – customers hate that, it’s a broken process.” The result is that applying for a mortgage often takes weeks, or even months.
Using machine learning, Experian is beginning to examine those data elements most commonly needed throughout the mortgage application process, in order to understand how that data can be located and delivered to where it’s needed in a faster, more efficient way. “It looks at ways to simplify the process, to reduce the amount of paper used and also to get to a decision much faster … with this new technology, we should be able to get to a decision in a few days, rather than weeks, and potentially much faster than that,” says Libenson.
Thanks to machine learning algorithms, the system will teach itself which data points are important, and which ones aren’t: “Over time, we may find out we don’t need to care about five years of tax returns – but what we need is five years of credit payments. So we reduce the workload on one dataset and increase it on another. My guess is that we will be ready to roll this out in 2018 or 2019, and by 2021 or 2022, we will find the datasets we are using will be quite different from the ones we initially used.”
Machine learning essentially means teaching computers to teach themselves by giving them access to lots and lots of data. This makes machine learning brilliant for automating complex and time-consuming, but fairly mundane, calculations, using data from huge and rapidly changing datasets. Because the process happens automatically, calculations can be done at an incredible speed.
Crucially, with machine learning, the larger the dataset, the more accurate the result. This means the output, be it analytics, insights or simulations, better reflect what’s likely to happen in the real world – in this case, whether a person will make their mortgage payments or not.
Ideas and insights you can steal
Experian is in an ideal position to spearhead technology in this field, largely thanks to the fact that banks and other institutions constantly come to the company for its data. Packaging these predictive machine learning-driven analytics as another valuable service is a great example of how a company can expand its offering, by capitalising on cutting-edge technology and ever-expanding datasets.