How big data and artificial intelligence are changing online lending

As digital lending continues to grow in size, businesses are looking for ways to make their services more efficient and cost effective for lenders and borrowers. And they believe artificial intelligence and big data hold the key to the future of lending.

Lenders traditionally make decisions based on the loan applicant’s credit rating, a three-digit number obtained from credit bureaus such as Experian and Equifax. Credit scores are calculated from data such as payment history, length of credit history, and line of credit amounts. They are used to determine the likelihood of applicants repaying their debts and to calculate the interest rate on loans. If your credit rating is low, you are considered an at-risk borrower, which means your loan application will either be refused or you will receive it at a high interest rate.

Digital lending platforms believe that this type of information does not paint a complete picture of a loan seeker’s creditworthiness. They set out to add hundreds and thousands of other data points to their process, not all of which are necessarily related to financial interactions. This can include information like your educational merits and certifications, your work history, and even trivial information like when you fall asleep, the websites you browse, your messaging habits, and your daily location patterns. .

Image: Business Insider

To be fair, big data can be a double-edged sword and create more confusion than clarity, and artificial intelligence has largely become a marketing term for companies who want to sell their products and services. But experts in the online lending industry believe it can have a big impact on the performance of fintech companies.

The data can allow businesses to create a more complete profile of a loan applicant. This can help make more accurate underwriting decisions, which translates into reduced defaults for lenders and lower interest rates for borrowers. It can also help automate parts – and maybe all – of the process.

How credit startups are leveraging AI

Upstart is a California-based peer-to-peer online lending company that improves lending with artificial intelligence. Upstart uses machine learning algorithms, a subset of AI, to make underwriting decisions. Machine learning can analyze and correlate huge amounts of customer data to find patterns that would otherwise require considerable manual effort or go unnoticed by human analysts. For example, it can determine if applicants are telling the truth about their earnings by looking at their employment history and comparing their data with that of similar clients. He can also find hidden models that might favor a candidate.

Upstart believes this may benefit people with limited credit histories, low incomes, and younger borrowers, who are typically hit by higher interest rates. The company has also been successful in automating 25% of its lowest risk loans, a number it expects to improve over time. This can save lenders a lot of time and energy, who will appreciate a return on their investment that requires less intervention on their part. The technology should be available to banks, credit unions, and even retailers who want to offer low-risk loans to their customers.

Before, a Chicago-based startup that offers unsecured loans ranging from $ 1,000 to $ 35,000, uses analytics and machine learning to streamline borrowing for applicants with a credit score below the acceptable threshold of traditional lending banks. The platform’s algorithms analyze 10,000 data points to assess the financial situation of consumers. For example, these algorithms help the platform identify applicants who have low FICO scores (below 650) but exhibit similar behavior to those with high credit scores.

The company also uses machine learning to detect fraud by comparing customer behavior with normal customer master data and eliminating outliers. The platform analyzes data such as the time people spend reviewing application questions, reading contracts, or reviewing pricing options.

Avant plans to expand its services to traditional banks wishing to start or expand their online lending business.

Remaining challenges

Digital loans are said to account for 10% of all loans in the United States and Europe, a figure that is constantly growing. The benefits of applying machine learning and analytics are obvious, and according to CB Insights, more than a dozen fintech startups are using the technology to assess loan applications and optimize the process.


Image: cbinsights

However, not everyone agrees that machine learning is the cure-all for all online lending problems. For example, many of these apps require you to download apps that collect all kinds of personal data. And as the Equifax hack shows, giving too much personal information to one company can have dire security and privacy consequences for you.

There is also the issue of algorithmic bias. Machine learning algorithms too often make decisions that reflect the biases and preferences of the people who provide them with training data. Experts fear this could introduce a whole new set of challenges for loan seekers. And the model has yet to prove its worth during a downturn or financial crisis.

However, proponents of machine learning-based lending are convinced that AI will eventually become an inherent part of online lending. In an interview with NPR, Dave Girouard, CEO of Upstart, said: “In 10 years there will be hardly any credit decision made that doesn’t have a flavor of machine learning behind it.

Source link

David A. Albanese