Using Alternative Data in Consumer Credit Underwriting

Getting credit is crucial for buying a house or starting a business. However, 45 million adults in the U.S. have little or no credit history, making it hard to get a reliable credit score. Traditional credit scoring relies on credit bureau data, but alternative data can provide a fuller picture.

What is alternative data?

Alternative data for loan underwriting extends beyond the information traditionally found in credit bureau reports¹ and includes: 

• Public records (property titles, address history, professional licenses) 
• Payment history with nonbank credit providers (point-of-sale financing, auto title loans, rent-to-own agreements, "buy now, pay later" plans) 
• Rent, utility, and phone contract payment history 
• Banking data (checking and savings account balances) to measure monthly cash flow 

Why use alternative data?  

A recent research paper² explored the predictive validity of the incorporation of alternative data in consumer credit scoring models. The authors found that credit applicants who benefit the most from the inclusion of alternative data are consumers with short or incomplete credit histories and applicants with an undergraduate or advanced university degree. Even details like the type of computer (device type and operating system) used for online applications can improve credit scoring models. 

Alternative data is also valuable when traditional credit data is sparse or outdated. The Consumer Financial Protection Bureau (CFPB) supports its use for more accurate credit assessments. However, it's underutilized in the U.S. due to challenges in integrating this data into credit scoring systems. 

FICO, a Teradata partner, developed a consumer credit scoring model called "FICO Score XD," a cutting-edge credit scoring model that uses alternative data. This includes payment histories from mobile phone and cable TV providers, as well as electric, gas, and other utility companies. By collaborating with Equifax® and LexisNexis® Risk Solutions, FICO taps into public records and payment data from the National Consumer Telecom & Utility Exchange (NCTUE).³ 

In countries like India, where many people don't have traditional bank relationships, lenders turn to mobile phone activity to build a "deep social footprint." This helps to improve credit scoring models by predicting defaults more accurately.  

According to the authors of a recent study: “Using various proxies based on the frequency and duration of daily incoming, outgoing, and missed calls that attempt to capture the breadth and strength of an individual’s social capital, we find that these measures are strongly correlated with the likelihood of default.”⁴ 

Despite the prevailing evidence of its value in assessing consumer creditworthiness, alternative data is not widely used by lenders in the U.S. While 92% of American consumers own a cell phone, only 5% of consumers have this payment data included in their traditional credit profile. Of the estimated 80 million renters in America, only 2.3% of their rent payments are reported to the credit bureaus.

Alternative data is underutilized by lenders because of the challenge associated with the delivery of alternative data into the environments where credit scoring models are developed and deployed.  

Realize the value of alternative data

Teradata’s QueryGrid, resilient high-speed data fabric that seamlessly integrates all data in all formats, can provide access to alternative data, in situ. ClearScape Analytics™ facilitates the data cleansing, transformation, entity resolution, and feature engineering necessary to make alternative data available for incorporation into the next generation of consumer credit scorecards, expanding the population of consumers with a credit score.


1. Laura Burrows, “What is Alternative Credit Scoring?” Equifax, 2023.
2. Mario DiMaggio, Dimuthu Ratnadiwakara, and Don Carmichael, “Invisible Primes: Fintech Lending With Alternative Data,” NBER, 2022.
3. Ben Luthi, “What Is Alternative Data?” FICO, 2022.
4. Sumit Agarwal, Shashwat Alok, Pulak Ghosh, and Sudip Gupta, “Financial Inclusion and Alternate Credit Scoring for the Millennials: Role of Big Data and Machine Learning in Fintech,” 2020.