Home >> Daily Dose >> The Big Data Revolution in Mortgage
Print This Post Print This Post

The Big Data Revolution in Mortgage

From online shopping to social media posts, the data trail consumers leave behind these days only grows longer and more telling. In fact, data scientists estimate that 90 percent of the world’s data was generated over the last two years alone. What does this mean for mortgage lenders?

While the era of big data is taking shape, no one can dispute that it’s arrived. When organized and analyzed, big data offers valuable insights into a consumer’s financial life that lenders can use to better assess borrowers who have long proved difficult to underwrite. Lenders can also drive new efficiencies in the loan production cycle. And lastly, lenders can design more effective marketing campaigns based on what big data tells them about their customers and target markets.

Why is Big Data a Big Deal?

Big data involves large and complex data sets that, when read, organized, and made searchable, can yield detailed insights about individual consumers or a targeted set of customers that an industry wants to sell its products to.

A related term, big data analytics, examines vast amounts of varied data sets to uncover hidden patterns, correlations, market trends, and additional insights about borrowers and the preferences of a company’s target market. The new benefits it brings to the table are speed and efficiency and more informed decision-making. The ability to work faster–and stay agile–gives organizations a competitive edge they didn’t have before.

For mortgage lenders, big data cuts across a wide swath of information. It can include internal company records on clients (loan files, bank statements, brokerage accounts), data obtained from third-party sources (generic credit scores, tax returns, credit card repayment rates) or information extracted from the internet (online purchasing patterns and information consumers share online social media posts).

Historically, all the information computers used was housed in highly structured databases, with separate fields for each piece of data, and companies spent lot of time and effort to input the relevant data and make sure it was clean and accurate. Big data includes information that originally was meant for consumption by people rather than machines—social media postings, visual images, and the like. But with recent advancements in hardware and software, computers can now ingest and analyze such information to detect patterns.

Better Assessing Borrowers with Thin Credit Files

By using the insights gleaned from big data, lenders can learn a lot more about borrowers with thin credit files—meaning people who haven’t tapped enough credit to be judged on just a generic credit score. For example, a lot of millennials don’t take out car loans, use credit cards, or work as salaried employees the way their parents did. However, they do pay cell phone bills, shop online and maintain LinkedIn profiles—all of which can help lenders to decide whether they’re a good credit risk.

In the same way that lenders can build alternative credit profiles for millennials, they can also do this when evaluating mortgage applicants from underserved communities, many of whom lack definitive credit histories.

Increasing Loan Production Efficiency

In the face of higher interest rates and declining origination volume, lenders need any leg up they can get to accelerate the production cycle, in a bid to control costs and preserve profit margins. Big data can prove useful in this regard. After a borrower applies for a loan, a lender can use publicly available information or data from third-party sources to help it verify an applicant’s income and assets.

In addition to enhancing data integrity, the application of big data through machine learning can help avoid last-minute delays by flagging a data point that requires further investigation. Machine learning is the type of artificial intelligence that enables a computer to parse data and identify patterns, relationships and anomalies within the data to arrive at conclusions or predictions.

For example, if the system uncovers a large deposit or withdrawal in a borrower’s bank account, the processor or underwriter can request clarification from the customer. This way, a problem that could otherwise hold up the loan is resolved long before closing day.

The speed and efficiency of approving and closing a loan directly affect production and underwriting costs. With more comprehensive, better-organized and easily searchable data, loan processors can deliver higher-quality files more quickly to underwriters. Underwriters can then focus on automated, flagged exceptions rather than “stare and compare” work. This can help shave days off the lending cycle timeline.

Getting More out of Marketing

By tapping into big data, lenders can gain additional insights into borrowers beyond what they can glean from credit scores and tax returns. This includes credit card transactions, income fluctuations reflected in bank accounts and news about significant life events, such as marriage, childbirth, and career changes learned through other publicly available information through social media. Once they aggregate information from different datasets, lenders can better segment customers and offer them products that best suit their needs at any point in their lives. With the use of machine learning algorithms, lenders can build models that identify correlations or hidden trends in borrower data to help build relationships with valuable customers and extend the reach of their marketing campaigns to prospects.

The success of any mortgage lender hinges on the scope and quality of its borrower data, the speed at which it can verify and process such data, and the way the lender uses such data to make its underwriting decisions. With the help of big data and the analytics that make sense of it, lenders stand to extend credit beyond their traditional client base and do it more quickly and efficiently than they’ve been able to thus far.

About Author: Dennis Tally

Dennis Tally is a Director in the Single-Family Data division at Freddie Mac, overseeing a team responsible for creating and enabling the Single-family data strategy, which includes managing several shared data assets such as the Big Data Analytic Platform and Single-Family Datamart. He is also the business owner of tools supporting data capabilities from business intelligence to machine learning and has represented Freddie Mac on data and analytic partners’ customer advisory boards for several years. Tally recently expanded his focus to transition Single- family work to the cloud and his team is actively working to deliver a hybrid-cloud capability in support of data science and analytics use cases.

Check Also

Fannie Mae Analysis Predicts a Rebounding Economy in 2025

"The economy is now slowing from the otherwise robust first estimate of third quarter growth," said Doug Duncan, Fannie Mae SVP and Chief Economist.