Leveraging Data-Centric AI for Better Business Outcomes

by Julie Lee 5 min read September 13, 2023

Group meeting

From science fiction-worthy image generators to automated underwriting, artificial intelligence (AI), big data sets and advances in computing power are transforming how we play and work. While the focus in the lending space has often been on improving the AI models that analyze data, the data that feeds into the models is just as important. Enter: data-centric AI.

What is a data-centric AI?

Dr. Andrew Ng, a leader in the AI field, advocates for data-centric AI and is often credited with coining the term. According to Dr. Ng, data-centric AI is, ‘the discipline of systematically engineering the data used to build an AI system.’1

To break down the definition, think of AI systems as a combination of code and data. The code is the model or algorithm that analyzes data to produce a result. The data is the information you use to train the model or later feed into the model to request a result.

Traditional approaches to AI focus on the code — the models. Multiple organizations download and use the same data sets to create and improve models. But today, continued focus on model development may offer a limited return in certain industries and use cases.

A data-centric AI approach focuses on developing tools and practices that improve the data.

You may still need to pay attention to model development but no longer treat the data as constant. Instead, you try to improve a model’s performance by increasing data quality. This can be achieved in different ways, such as using more consistent labeling, removing noisy data and collecting additional data.2

Data-centric AI isn’t just about improving data quality when you build a model — it’s also part of the ongoing iterative process. The data-focused approach should continue during post-deployment model monitoring and maintenance.

Data-centric AI in lending

Organizations in multiple industries are exploring how a data-centric approach can help them improve model performance, fairness and business outcomes. For example, lenders that take a data-centric approach to underwriting may be able to expand their lending universe, drive growth and fulfill financial inclusion goals without taking on additional risk.

Conventional credit scoring models have been trained on consumer credit bureau data for decades. New versions of these models might offer increased performance because they incorporate changes in the economic landscape, consumer behavior and advances in analytics. And some new models are built with a more data-centric approach that considers additional data points from the existing data sets — such as trended data — to score consumers more accurately. However, they still solely rely on credit bureau data.

Explainability and transparency are essential components of responsible AI and machine learning (a type of AI) in underwriting. Organizations need to be able to explain how their models come to decisions and ensure they are behaving as expected.

Model developers and lenders that use AI to build credit risk models can incorporate new high-quality data to supplement existing data sets. Alternative credit data can include information from alternative financial services, public records, consumer-permissioned data, and buy now, pay later (BNPL) data that lenders can use in compliance with the Fair Credit Reporting Act (FCRA).*

The resulting AI-driven models may more accurately predict credit risk — decreasing lenders’ losses. The models can also use alternative credit data to score consumers that conventional models can’t score.

Infographic: From initial strategy to results — with stops at verification, decisioning and approval — see how customers travel across an Automated Loan Underwriting Journey.

Business benefit of using data-centric AI models

Financial services organizations can benefit from using a data-centric AI approach to create models across the customer lifecycle. That may be why about 70 percent of businesses frequently discuss using advanced analytics and AI within underwriting and collections.3

Many have gone a step further and implemented AI. Underwriting is one of the main applications for machine learning models today, and lenders are using machine learning to:4

  • More accurately assess credit risk models.
  • Decrease model development, deployment and recalibration timelines.
  • Incorporate more alternative credit data into credit decisioning.

AI analytics solutions may also increase customer lifetime value by helping lenders manage credit lines, increase retention, cross-sell products and improve collection efforts. Additionally, data-centric AI can assist with fraud detection and prevention.

Case study: Learn how Atlas Credit, a small-dollar lender, used a machine learning model and loan automation to nearly doubled its loan approval rates while decreasing its credit risk losses.

How Experian helps clients leverage data-centric AI for better business outcomes

During a presentation in 2021, Dr. Ng used the 80-20 rule and cooking as an analogy to explain why the shift to data-centric AI makes sense.5 You might be able to make an okay meal with old or low-quality ingredients. However, if you source and prepare high-quality ingredients, you’re already 80% of the way toward making a great meal.

Your data is the primary ingredient for your model — do you want to use old and low-quality data?

Experian has provided organizations with high-quality consumer and business credit solutions for decades, and our industry-leading data sources, models and analytics allow you to build models and make confident decisions.

If you need a sous-chef, Experian offers services and has data professionals who can help you create AI-powered predictive analytics models using bureau data, alternative data and your in-house data.

Learn more about our AI analytics solutions and how you can get started today.

1DataCentricAI. (2023). Data-Centric AI.
2Exchange.scale (2021). The Data-Centric AI Approach With Andrew Ng.
3Experian (2021). Global Insights Report September/October 2021.
4FinRegLab (2021). The Use of Machine Learning for Credit Underwriting: Market & Data Science Context. 
5YouTube (2021). A Chat with Andrew on MLOps: From Model-Centric to Data-Centric AI
*Disclaimer: When we refer to “Alternative Credit Data,” this refers to the use of alternative data and its appropriate use in consumer credit lending decisions, as regulated by the Fair Credit Reporting Act. Hence, the term “Expanded FCRA Data” may also apply in this instance and both can be used interchangeably.

Related Posts

New data indicate signs of increased VantageScore 4.0 adoption. Recent Experian Capital Markets data reporting points to gradual growth in VantageScore 4.0 adoption, and more loans beginning to appear in a larger share of GSE pools.

November 20, 2026 by Angad Paintal
What Is a Ransomware Attack? How to Prepare and Respond

Ransomware attacks can create challenges that extend far beyond an organization’s IT systems. When critical applications become unavailable or sensitive information is compromised, businesses may face operational disruption, financial losses and difficult decisions about how to support affected customers. While cybersecurity defenses are essential, organizations also need clear response procedures, coordinated communication and recovery plans. Understanding how ransomware attacks happen, their potential impact and the steps organizations can take to prepare can help businesses respond more effectively when an incident occurs. What is a ransomware attack? A ransomware attack is a type of cyberattack in which criminals use malicious software or extortion tactics to demand payment from an organization. Traditionally, ransomware encrypts files or systems, preventing authorized users from accessing information until a ransom is paid. Some attackers also steal sensitive data and threaten to release it unless their demands are met. These tactics may occur separately or together, creating challenges for organizations trying to restore operations and protect sensitive information. Paying a ransom does not guarantee that attackers will restore access, delete stolen information or refrain from making additional demands. How do ransomware attacks happen? Ransomware attacks often begin when cybercriminals gain unauthorized access to an organization’s systems or accounts. Once inside, attackers may attempt to expand their access, steal information or deploy malicious software. Common attack methods include: Phishing and social engineering: Deceptive emails or messages that trick employees into opening malicious attachments, visiting harmful websites or sharing login credentials Compromised credentials: Stolen passwords or authentication information used to access business systems and accounts Unpatched vulnerabilities: Security weaknesses in software, servers or network devices that attackers exploit Third-party access: Compromised vendors or connected systems that provide a potential entry point Malicious downloads: Harmful software installed through deceptive websites, compromised applications or unsafe downloads Understanding these methods can help organizations identify potential weaknesses and strengthen their security practices. How do ransomware attacks affect businesses and customers? The consequences of a ransomware attack depend on the systems affected, the information involved and the organization's ability to contain the incident. Business disruption and financial losses When critical systems become unavailable, organizations may experience interruptions to customer service, payment processing, internal operations or other essential functions. The financial impact can be significant. According to the FBI's 2025 Internet Crime Report, reported ransomware-related losses reached approximately $32.3 million, up from $12.5 million in 2024. These figures do not capture the full financial impact of ransomware incidents, including business interruption, recovery expenses and other indirect costs. Customer data exposure and fraud risks Some ransomware incidents involve the theft of sensitive information, potentially exposing customers to identity theft or fraud. If attackers obtain login credentials or personal information, organizations may also need to consider related threats, including account takeover. Customer trust and reputation Customers expect organizations to protect their information and communicate clearly when incidents affect them. Delayed or confusing communication may create additional uncertainty. A coordinated response can help organizations provide timely information and appropriate support to affected individuals. What should organizations do after a ransomware attack? When a ransomware incident is suspected, organizations should activate their incident response procedures and work with qualified professionals to assess and contain the threat. Important response steps include: Activate the response team: Bring together IT, cybersecurity, legal, privacy, communications and leadership teams as appropriate. Contain the incident: Identify affected systems and take steps to limit further unauthorized activity while preserving relevant evidence. Investigate the impact: Determine which systems and information may have been compromised, including whether sensitive data was accessed or removed. Evaluate notification requirements: Work with legal and privacy advisers to determine applicable regulatory, contractual and customer communication obligations. Support affected customers: Prepare clear communications and appropriate resources when personal information has been exposed. An established data breach response strategy can help organizations coordinate customer notification and support activities following an incident. How can organizations prepare for and recover from ransomware attacks? Organizations can prepare for ransomware attacks by combining security controls, tested backups, employee training and a documented incident response plan. Recovery planning should also address how teams will restore systems, assess data exposure and communicate with affected customers. Key preparedness measures include: Maintain secure backups: Keep protected backups and regularly test restoration procedures. Strengthen access controls: Implement multifactor authentication and limit access to sensitive systems. Update software: Address known vulnerabilities through consistent patch management. Train employees: Help staff recognize phishing attempts and suspicious activity. Monitor security threats: Use appropriate detection and monitoring tools to identify potential attacks. Test response plans: Conduct exercises that evaluate technical recovery, communication and decision-making responsibilities. Following an incident, recovery should focus on restoring systems safely, addressing remaining vulnerabilities and evaluating potential risks to affected individuals. Organizations may also need to consider whether compromised information could contribute to additional fraud. Depending on the circumstances, fraud prevention solutions may support broader identity risk management efforts. Security teams should also evaluate related threats, including automated bot attacks, when assessing potential misuse of compromised accounts or credentials. Once operations are restored, reviewing lessons learned can help organizations strengthen their security controls, response procedures and future preparedness. How can breach response planning help protect customers? Ransomware preparedness should account for both operational recovery and the potential impact on customers. If sensitive information is compromised, organizations may need to coordinate notifications, respond to customer questions and provide appropriate support. Experian® offers data breach resolution services that help organizations plan for and manage customer-facing aspects of a breach, including notification management and response support. By establishing response procedures before an incident, organizations can improve coordination and prepare to address customer needs when a breach occurs. Prepare for a more coordinated breach response Explore Experian's data breach response solutions and learn how to plan for customer notification and support. Explore data breach response solutions Download the 2027 Data Breach Response Guide

November 20, 2026 by Julie Lee
How GenAI Fraud Bots Fly Under the Radar (and How to Ground Them Before It’s Too Late)

Today’s AI-powered fraud bots are exceptionally good at mimicking human behavior. Learn why a modern defense strategy is key.

November 18, 2026 by Laura Burrows

Subscribe to our Newsletter

Enter your name and email for the latest updates.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Subscribe to our Newsletter

Don't miss out on the latest industry trends and insights!
Subscribe