Reduce Errors in Consumer Reports with AI-Based Identity Resolution

Identity Resolution, Record Management, Risk Management

Consumer reporting entities such as credit bureaus play a critical role in many decisions made about individuals and their reporting affects hundreds of millions of people. They collect consumer data from many sources and aggregate the information into reports detailing a person’s credit history, previous addresses, and other relevant life activities. Lenders, credit card companies, insurance companies, and others rely on this information to assess risk and eligibility for credit cards, home-mortgage/auto loans, or insurance coverage. Employers use these reports for prescreening and background checks of current and prospective employees. Rental housing and payday loan services also rely on consumer reports.

Assembling accurate consumer reports is not a trivial task. Information flows in on a continuous basis from multiple sources such as credit card companies, collection agencies, and public records like court judgments and bankruptcy filings. Sources don’t always identify the individuals in the same way. Names may differ due to word order variations (e.g., first-last vs. last-first), maiden names, married names, missing elements (e.g., middle names, suffixes), nicknames, mismatching addresses, and misspellings. Addresses, date of birth, social security numbers and other key information may also contain errors.

Yet, when so much is at stake, information accuracy is of utmost importance.  Incorrectly merged information can have a severe negative impact on consumers’ ability to secure credit, employment, or housing. They are also a liability for consumer reporting entities if they are determined to have too many errors or are too expensive to correct. On the regulatory side, agencies like the Consumer Financial Protection Bureau (CFPB) and legislation like the Fair Credit Reporting Act (FCRA) require consumer reporting entities to assure maximum possible accuracy of consumer information. On the consumer side, attorneys may pursue monetary compensation for loss of credit or employment opportunities as well as damage to reputation.

Recent studies show that there is certainly much room for improvement in accurately resolving records from multiple sources to the correct individual. According to the FTC, one of every five American consumers — 40 million Americans — had an error on his or her credit report and 10 million were potentially overpaying as a result in the form of more expensive credit, failing to obtain credit, or even loss of potential job opportunities.

What to Look for in Identity Resolution to Ensure Maximum Accuracy of Consumer Reports

Identity Resolution is about figuring out what records represent the same entity, in this case the same consumer. In order to ensure the maximum accuracy of consumer reports, an Identity Resolution system must have the following properties:

  1. High accuracy. Merging records requires performing intelligent matching of various fields, including not just names but also other key attributes such as date of birth, place of birth, and address. The confidence of the match is determined by the combination of evidence from multiple attributes. Those multiple attributes typically involve various entity types, such as people, organizations, places, and addresses. For example, accurately matching information about a specific individual may rely on knowledge about their spouse (person), child (person), employer (organization), education (organization), place of birth (place), date of birth (date), and home address (address) among others. NetOwl’s Identity Resolution leverages its award-winning machine learning-based, multicultural, multi-lingual name matching product to enable sophisticated name matching of various entity types across different languages.
  2. Scalable and real-time. Consumer reports are a true Big Data problem. Identity Resolution must support scalable, real-time searching of massive databases with hundreds of millions of records. NetOwl can match new records against large quantities of existing records in real time.
  3. On premise. Given the sensitive nature of consumer data, identity resolution must be available on premise. NetOwl is available for installation in secure environments and offers a REST API for easy integration with new or existing record processing systems.
  4. Tunable. Application-specific business rules determine what combination of record attributes should be matched and how important each attribute is to the overall matching score.

NetOwl’s AI-based Identity Resolution software provides a high-accuracy, scalable, fast, and tunable solution to merge customer data from multiple sources. It allows consumer reporting entities to maximize the accuracy of their consumer reports, thus reducing compliance and liability risk.