Rice research explores how shopping data could reshape credit scores

houston voices

Everyday data like grocery store receipts can help expand access to credit and support upward mobility. Photo by Boxed Water Is Better on Unsplash

More than a billion people worldwide can’t access credit cards or loans because they lack a traditional credit score. Without a formal borrowing history, banks often view them as unreliable and risky. To reach these borrowers, lenders have begun experimenting with alternative signals of financial reliability, such as consistent utility or mobile phone payments.

New research from Rice Business builds on that approach. Previous work by assistant professor of marketing Jung Youn Lee showed that everyday data like grocery store receipts can help expand access to credit and support upward mobility. Her latest study extends this insight, using broader consumer spending patterns to explore how alternative credit scores could be created for people with no credit history.

Forthcoming in the Journal of Marketing Research, the study finds that when lenders use data from daily purchases — at grocery, pharmacy, and home improvement stores — credit card approval rates rise. The findings give lenders a powerful new tool to connect the unbanked to credit, laying the foundation for long-term financial security and stronger local economies.

Turning Shopping Habits into Credit Data

To test the impact of retail transaction data on credit card approval rates, the researchers partnered with a Peruvian company that owns both retail businesses and a credit card issuer. In Peru, only 22% of people report borrowing money from a formal financial institution or using a mobile money account.

The team combined three sets of data: credit card applications from the company, loyalty card transactions, and individuals’ credit histories from Peru’s financial regulatory authority. The company’s point-of-sale data included the types of items purchased, how customers paid, and whether they bought sale items.

“The key takeaway is that we can create a new kind of credit score for people who lack traditional credit histories, using their retail shopping behavior to expand access to credit,” Lee says.

The final sample included 46,039 credit card applicants who had received a single credit decision, had no delinquent loans, and made at least one purchase between January 2021 and May 2022. Of these, 62% had a credit history and 38% did not.

Using this data, the researchers built an algorithm that generated credit scores based on retail purchases and predicted repayment behavior in the six months following the application. They then simulated credit card approval decisions.

Retail Scores Boost Approvals, Reduce Defaults

The researchers found that using retail purchase data to build credit scores for people without traditional credit histories significantly increased their chances of approval. Certain shopping behaviors — such as seeking out sale items — were linked to greater reliability as borrowers.

For lenders using a fixed credit score threshold, approval rates rose from 15.5% to 47.8%. Lenders basing decisions on a target loan default rate also saw approvals rise, from 15.6% to 31.3%.

“The key takeaway is that we can create a new kind of credit score for people who lack traditional credit histories, using their retail shopping behavior to expand access to credit,” Lee says. “This approach benefits unbanked applicants regardless of a lender’s specific goals — though the size of the benefit may vary.”

Applicants without credit histories who were approved using the retail-based credit score were also more likely to repay their loans, indicating genuine creditworthiness. Among first-time borrowers, the default rate dropped from 4.74% to 3.31% when lenders incorporated retail data into their decisions and kept approval rates constant.

For applicants with existing credit histories, the opposite was true: approval rates fell slightly, from 87.5% to 84.5%, as the new model more effectively screened out high-risk applicants.

Expanding Access, Managing Risk

The study offers clear takeaways for banks and credit card companies. Lenders who want to approve more applications without taking on too much risk can use parts of the researchers’ model to design their own credit scoring tools based on customers’ shopping habits.

Still, Lee says, the process must be transparent. Consumers should know how their spending data might be used and decide for themselves whether the potential benefits outweigh privacy concerns. That means lenders must clearly communicate how data is collected, stored, and protected—and ensure customers can opt in with informed consent.

Banks should also keep a close eye on first-time borrowers to make sure they’re using credit responsibly. “Proactive customer management is crucial,” Lee says. That might mean starting people off with lower credit limits and raising them gradually as they demonstrate good repayment behavior.

This approach can also discourage people from trying to “game the system” by changing their spending patterns temporarily to boost their retail-based credit score. Lenders can design their models to detect that kind of behavior, too.

The Future of Credit

One risk of using retail data is that lenders might unintentionally reject applicants who would have qualified under traditional criteria — say, because of one unusual purchase. Lee says banks can fine-tune their models to minimize those errors.

She also notes that the same approach could eventually be used for other types of loans, such as mortgages or auto loans. Combined with her earlier research showing that grocery purchase data can predict defaults, the findings strengthen the case that shopping behavior can reliably signal creditworthiness.

“If you tend to buy sale items, you’re more likely to be a good borrower. Or if you often buy healthy food, you’re probably more creditworthy,” Lee explains. “This idea can be applied broadly, but models should still be customized for different situations.”

---

This article originally appeared on Rice Business Wisdom. Written by Deborah Lynn Blumberg

Anderson, Lee, and Yang (2025). “Who Benefits from Alternative Data for Credit Scoring? Evidence from Peru,” Journal of Marketing Research.

From Your Site Articles
Grocery purchase data can accurately predict credit risk for individuals without traditional credit scores, potentially broadening the pool of qualified loan applicants. Photo via Unsplash

Houston researchers find alternate data for loan qualification

houston voices

Millions of consumers who apply for a loan to buy a house or car or start a business can’t qualify — even if they’re likely to pay it back. That’s because many lack a key piece of financial information: a credit score.

The problem isn’t just isolated to emerging economies. Exclusion from the financial system is a major issue in the United States, too, where some 45 million adults may be denied access to loans because they don’t have a credit history and are “credit invisible.”

To improve access to loans and peoples’ economic mobility, lenders have started looking into alternative data sources to assess a loan applicant’s risk of defaulting. These include bank account transactions and on-time rental, utility and mobile phone payments.

A new article by Rice Business assistant professor of marketing Jung Youn Lee and colleagues from Notre Dame and Northwestern identifies an even more widespread data source that could broaden the pool of qualified applicants: grocery store receipts.

As metrics for predicting credit risk, the researchers found that the types of food, drinks and other products consumers buy, and how they buy them, are just as good as a traditional credit score.

“There could be privacy concerns when you think about it in practice,” Lee says, “so the consumer should really have the option and be empowered to do it.” One approach could be to let consumers opt in to a lender looking at their grocery data as a second chance at approval rather than automatically enrolling them and offering an opt-out.

To arrive at their findings, the researchers analyzed grocery transaction data from a multinational conglomerate headquartered in a Middle Eastern country that owns a credit card issuer and a large-scale supermarket chain. Many people in the country are unbanked. They merged the supermarket’s loyalty card data and issuer’s credit card spending and payment history numbers, resulting in data on 30,089 consumers from January 2017 to June 2019. About half had a credit score, 81% always paid their credit card bills on time, 12% missed payments periodically, and 7% defaulted.

The researchers first created a model to establish a connection between grocery purchasing behavior and credit risk. They found that people who bought healthy foods like fresh milk, yogurt and fruits and vegetables were more likely to pay their bills on time, while shoppers who purchased cigarettes, energy drinks and canned meat tended to miss payments. This held true for “observationally equivalent” individuals — those with similar income, occupation, employment status and number of dependents. In other words, when two people look demographically identical, the study still finds that they have different credit risks.

People’s grocery-buying behaviors play a factor in their likelihood to pay their bills on time, too. For example, cardholders who consistently paid their credit card bill on time were more likely to shop on the same day of the week, spend similar amounts across months and buy the same brands and product categories.

The researchers then built two credit-scoring predictive algorithms to simulate a lender’s decision of whether or not to approve a credit card applicant. One excludes grocery data inputs, and the other includes them (in addition to standard data). Incorporating grocery data into their decision-making process improved risk assessment of an applicant by a factor of 3.11% to 7.66%.

Furthermore, the lender in the simulation experienced a 1.46% profit increase when the researchers implemented a two-stage decision-making process — first, screening applicants using only standard data, then adding grocery data as an additional layer.

One caveat to these findings, Lee and her colleagues warn, is that the benefit of grocery data falls sharply as traditional credit scores or relationship-specific credit histories become available. This suggests the data could be most helpful for consumers new to credit.

Overall, however, this could be a win-win scenario for both consumers and lenders. “People excluded from the traditional credit system gain access to loans,” Lee says, “and lenders become more profitable by approving more creditworthy people.”

------

This article originally ran on Rice Business Wisdom based on research by Rice University's Jung Youn Lee, Joonhyuk Yang (Notre Dame) and Eric Anderson (Northwestern). “Using Grocery Data for Credit Decisions.” Forthcoming in Management Science. 2024: https://doi.org/10.1287/mnsc.2022.02364.


Give credit where credit is due. The Woodlands falls in the "very good" category. Photo courtesy of Local Government Federal Credit Union

Houston suburbs charge ahead with some of the highest credit scores in Texas

fit for fico

Give the residents of The Woodlands some credit. They’re able to brag about achieving some of the highest credit scores in Texas.

A new study from personal finance website WalletHub shows the median credit score of a Woodlands resident is 757. Among the 2,572 U.S. cities covered in the study, The Woodlands nabs a 287th-place tie for cities with the highest median credit score.

FICO, the primary producer of credit scores in the U.S., characterizes 757 as a “very good” credit score. On the FICO scale, credit scores range from 300 to 850. A credit score anywhere from 740 to 799 is above the U.S. average “and demonstrates to lenders that the borrow is very dependable,” according to FICO.

WalletHub based the study on September 2021 data from TransUnion, one of the three major credit-reporting bureaus. In the study, The Villages, a retirement community in Florida, is the only city where the median credit score is above 800 — 806, to be exact.

Two other Houston-area suburbs — Montgomery and Friendswood — ranked among Texas cities for the highest credit scores, coming in with a median credit score of 738 and 732, respectively.

Here are the other cities in the top 15 statewide:

  • Colleyville (Dallas-Fort Worth), 777, 23rd nationally.
  • Flower Mound, 762, tied for 185th place nationally.
  • Coppell (Dallas-Fort Worth), 758, tied for 262nd place nationally.
  • The Woodlands (Houston), 757, tied for 287th nationally.
  • Keller (Dallas-Fort Worth), 756, tied for 300th nationally.
  • Allen (Dallas-Fort Worth), 750, tied for 428th nationally.
  • Georgetown (Austin), 749, tied for 446th nationally.
  • Frisco (Dallas-Fort Worth), 748, tied for 467th nationally.
  • Cedar Park (Austin), 743, tied for 568th nationally.
  • Plano (Dallas-Fort Worth), 740, tied for 629th nationally.
  • Montgomery (Houston), 738, tied for 681st nationally.
  • Friendswood (Houston), 732, tied for 784th nationally.
  • Rockwall (Dallas-Fort Worth), 732, tied for 784th nationally.

Among Texas’ biggest cities, Austin is the only one where the median credit score exceeds 700. In the Capital City, the median score is 713, tied for 1,208th nationally. San Antonio is next in line, at 664 (tied for 2,236th nationally), followed by Houston (662, tied for 2281st nationally), Dallas (661, tied for 2,299th nationally), and Fort Worth (615.5, tied for 2,545th nationally).

Bad news for Sugar Land, which is the only Texas city with a median credit score below 600. According to the study, the median score there is 571, putting it in 2,563rd place nationally. FICO identifies that as a “poor” credit score.

J. Keith Baker, a CPA and certified financial planner who teaches at Dallas College’s North Lake campus in Irving, tells WalletHub that the best way to improve or maintain your credit score is to pay your credit card balances in full every month.

“Some folks will close a credit card account thinking it will help them manage their spending and protect them from identity theft since they are not using an account,” Baker says. “While this may make sense for an individual’s financial situation, do not assume it will automatically improve your credit scores.”

------

This article originally ran on CultureMap.

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Property Showcase

Texas university's new flight academy opens at Houston Spaceport

cleared for takeoff

The vehicles may not have “student driver” stickers on them, but Texas Southern University has moved a dozen planes into its new training facility at the Houston Spaceport, opening the way for student flyers to use the facility.

TSU previously reached a deal with Houston Airports and the City of Houston in 2023 to house its prospective Flight Academy at Ellington Field. At the time, TSU had a small fleet of nine planes for student use, but a $5.5 million investment from the city greatly expanded the space available.

The Flight Academy includes a 20,000-square-foot hangar that serves as a TSU satellite campus. The school now has a fleet of 12 Cirrus SR20 aircraft that were acquired last year through state and alumni funding. An additional 4,500 square feet is used as classroom and office space. An 8,000-gallon fuel tank will support flight training operations.

TSU first launched its Aviation Science Management program in 1986 and added a professional pilot program in 2016. The school is now part of the United Airlines pipeline program and has also forged relationships with Delta and Southwest.

“I want to commend Texas Southern University and Houston Airports for their leadership and partnership in advancing aviation education right here in our city,” Houston City Councilwoman Dr. Carolyn Evans-Shabazz in a press release.

“It connects our students to high-paying, high-demand careers in aviation and aerospace. This is how we grow a city in the right way—by investing in workforce development, aligning education with industry and making sure our residents are prepared to lead in the industries of tomorrow. Houston is already a global leader in aerospace and projects like this strengthen that position even further, especially here at Ellington, where innovation and opportunity continue to take flight.”

The City of Houston signed an agreement to continue funding the academy for five years.

Amazon launches ultrafast, 30-minute delivery service across Houston

Amazon Now

More than 20 years after it redefined fast shipping, Amazon is preparing to raise the bar on consumer expectations again by offering to fulfill customers' most urgent product needs in Houston and other parts of the world in a half-hour or less for an extra fee.

The company, which revolutionized online shopping in 2005 with two-day deliveries for Prime members, is rapidly opening small order-processing hubs in dozens of U.S. and foreign cities to cater to shoppers who can't or don't want to wait for cough medicine to relieve flu symptoms or tomatoes for tonight's dinner salad.

The ultrafast service, called Amazon Now, first launched in India last June. Amazon says 30-minute deliveries now are also available in urban areas of the United States, Brazil, Mexico, Japan, the United Arab Emirates, the United Kingdom.

The mini-warehouses devoted to Amazon Now are about the size of a CVS drugstore. They stock about 3,500 products for expedited delivery, including beer, diapers, pet food, meat, nonprescription medications, playing cards and cellphone charging cables.

“We know that customers love speed and always have,” Beryl Tomay, Amazon’s head of transportation, told The Associated Press on Monday. “What we see customers doing, when we offer faster speeds, are they purchase more from Amazon. And Amazon becomes more top of mind for that or other types of items as well.”

In the U.S., the company first tested Amazon Now in Seattle, the home of its headquarters, and in Philadelphia. Most residents of the Dallas-Fort Worth area and Atlanta now have access as well. The service is also live in Dallas-Fort Worth, Denver, Minneapolis, Phoenix, Oklahoma City, Orlando, and dozens of other cities, Amazon said, with New York City and others expected by year-end.

The service charges for Amazon Now start at $3.99 for Prime members, who pay an annual fee of $139, and $13.99 for non-members. A $1.99 small basket fee applies to orders under $15, Amazon said.

The company's bet on a need for speed also comes as some consumers are rebelling against rushed deliveries as they weigh the potential impact on the environment and the workers tasked with preparing orders at a rapid rate.

Amazon’s approach
A relentless focus on speed helped Amazon build a logistics and e-commerce empire. After it made two days the new delivery time normal, Amazon moved into one-day and same-day deliveries for its Prime members. This spring, the company began making 90,000 products available in one hour or three hours at an extra cost.

The scaled down and sped up microhubs that are designed to handle 30-minute orders represent another step in Amazon's pursuit.

Only a handful of people prepare orders from aisles of shelves in the 5,000- to 10,000-square-foot facilities, unlike the sprawling fulfillment centers storing millions of items where Amazon employs a mix of human workers and robotics to pick and pack orders.

Amazon tailors the product inventory to each location and uses artificial intelligence and other technology to analyze what customers buy, as well as when and how often. The most popular U.S. purchases so far include soap, toothpaste, mouthwash, toilet plungers, bananas, limes and wireless earbuds, Amazon said.

The competition
Amazon’s attempt to up the instant gratification ante provides direct competition to on-demand food delivery platforms like Instacart, Uber Eats, DoorDash and Grubhub, which don't have the scale of the e-commerce titan, according to independent retail analyst Bruce Winder.

“What Amazon brings is their prowess in supply chain,” Winder said.

These smaller companies said they don't see Amazon as a threat, though, citing the hundreds of thousands of items they are able to deliver to users' doorsteps by partnering with various merchants and restaurants.

“DoorDash has a mission to empower grocers and retailers and augment their existing footprint, not to replace them,” DoorDash spokesperson Ali Musa said in an emailed statement. “We win only when they win, which is how we can offer over half a million grocery and retail items in under an hour across the country.”

Amazon also is in a race with Walmart to become the retailer that reliably gets orders to online shoppers in under an hour.

For an additional $10 on top of standard delivery charges, shoppers can place Walmart Express Delivery orders from among more than 100,000 products that are guaranteed to arrive in an hour. Many customers, however, are receiving the items under 30 minutes, Walmart CEO John Furner told analysts in February.

Domino's cautionary tale
Companies have promised deliveries in 30 minutes or less before, but the landscape also is littered with failed attempts to break the speed barrier.

The COVID-19 pandemic produced a flurry of companies that promised 10- to 15-minute grocery deliveries from microwarehouses in dense neighborhoods, according to Sucharita Kodali, an analyst at market research firm Forrester Research.

But soaring operating costs, low customer loyalty and the drying up of investor money ultimately caused most to fail before the pandemic was over, analysts said.

Domino’s in 1984 pushed a guarantee that customers would receive their pizzas for free if they weren't delivered in under a half-hour. The company amended the “30 minutes or it’s free” policy after two years, providing only a $3 discount for late deliveries.

The promotion helped Domino’s win market share, but it ended up tarnishing the company's reputation. It dropped the guarantee in December 1993 after a string of crashes and lawsuits involving drivers racing to meet the deadline.

Brad Jashinsky, a retail analyst at information technology research and consulting firm Gartner, said he thinks Amazon should take the pizza chain's experience as a cautionary tale.

“You get in trouble when you start overpromising something like that,” he said.

Amazon won't be making any time guarantees and instead plans to keep customers who chose the 30-minute delivery option updated on the progress of their orders, Tomay said.

“There's no rushing either in our building workers or the gig workers,” she said.

Taking it slow
Kodali thinks Amazon will need a lot of people placing orders around the same time from the same or adjacent apartment buildings for the 30-minute service to be cost-effective.

Consumers may appreciate rapid receipt of products like toilet paper and batteries, but retailers and logistics experts said they also see some online shoppers, especially members of Generation Z, choosing no-rush shipping for products they don't need in a hurry.

Amazon for several years has invited customers to skip one- or two-day delivery and to receive their orders on the same day in as few parcels as possible. Consolidating orders into fewer packages by electing to have them delivered at the same time cuts down on boxes, shipping envelopes and fuel use, analysts said.

“The millennials who came to age in an era that was on fast delivery came to expect it de facto, whereas ... Gen Z is more accepting of a slower speed than previous generations before them,” said Darby Meegan, a general manager at Flexport, a supply chain and logistics company that fulfills orders for thousands of online merchants.

Still, Amazon executives have cited positive early results for Amazon Now in India, where they said Prime members tripled their requests for 30-minute deliveries once they started using the service.

Amazon Now also is attracting more repeat American customers, Tomay said.

“It’s in early days and time will tell,” she said. “I think that it will be interesting to see how it evolves.”

Houston company partners on AI-powered medical support for space missions

AI in space

Houston-based Aexa Aerospace has partnered with SpacePort Australia (SPA) to build medical AI solutions for space crews.

Known as The Hamilton Project, the collaboration aims to complete the training and refinement of a “deductive medical AI model” designed to aid and treat astronauts and space travellers. With limited to no real-time access to doctors on Earth during space missions, the project's goal is to create an AI model that would serve as a medical resource.

“‘The Hamilton Project’ is a sophisticated AI model, integrating academic and clinical knowledge in a unique way,” Aexa founder and CEO Feranando De La Peña Llaca said in a news release. “It is paving the way for future autonomous attending.”

The project is named after NASA flight surgeon Dr. Douglas Hamilton, who participated in 50 missions.

SPA, an independent research organization, will bring its practical medical knowledge and clinical experience to The Hamilton Project, which builds on Australia’s rural and remote medical training programs. SPA founder Dr. Gabrielle Caswell brings 20 years of remote medicine experience that SPA believes will help address the issues that could be encountered in space.

“Rural general practitioners in Australia practice ‘pre-cradle to grave’ medicine, including areas considered sub-specialities in most western countries: OBYN, paediatrics, trauma management, anaesthetics, general surgery, mental health and geriatrics,” Caswell added in the release. “This broad clinical skill set encompasses all stages and phases of human life. And importantly practitioners are also trained in the management of severe trauma. "It is anticipated that doctors and medical staff will become embedded into missions, and all these skills will be required over time, to create successful space economic zones.”

Aexa Aerospace’s previous work includes developing holographic medical devices that have been trialled on the International Space Station. Read more here.

View All Listings