Archive Links

Consumer Archive
CU System Archive
Market Archive
Products Archive
Washington Archive

News Now

CU System
Filene Report: Mine Big Data To Predict Member Behavior
MADISON, Wis.  (7/22/13)--Credit union members follow simple paths during their life cycle and adopt different consumer products at each stage, according to a new Filene Research Institute report.
The report, "Big Data and Credit Unions: Machines Learning in Member Transactions," by Phillip Kallerhoff, shows that some simple patterns evolve using big data and machine learning--a branch of artificial intelligence that focuses on the construction and study of systems that can learn from data.
Five credit unions in the U.S. and Canada offered their members' anonymous profile information and transaction details to the researcher, who used variables as diverse as gender, product balances, credit score, income and transaction amounts--big data--to search for revealing correlations to predict member behavior.
Companies such as Amazon, Google, Walmart and Wells Fargo are turning to big data for insights that will help them serve customers and capture market share. Big data is the analysis of huge data sets. While individual credit unions may not have the resources of a corporate giant, advances in data storage and software tools mean that credit unions can start using similar tools and deriving similar value, the report said.

The five credit unions in the study each looked for different information, and the plasticity of big data means that, with the right tools and the right inputs, they could discover different insights. Because a machine learning project is only as helpful as the data that flow into it, the credit unions got more specific insights. But their combined data still offer generalizable findings for all credit unions.

Some key findings of the report were:
  • Credit unions can mine members' transactional data to predict member behavior and product life cycles, improve profitability and reduce risk.
  • The relationship between health and finances can be used as an example of looking at external factors to predict member behavior.
  • Applying machine learning to transaction data helps credit unions identify and leverage the paths that members follow.
  • Big data add another dimension to credit scores, allowing lenders to improve underwriting and use transaction information to take different risks on members than a standard credit score allows.
To access the report use the link.
RSS print
News Now LiveWire
.@RepDennyHeck to @NWCUA Amplify conference audience: "More often than not, CUs are part of the solution"
8 hours ago
LA Laker and NBA Legend Earvin "Magic" Johnson was the keynote speaker Tuesday @CCULReach, hosted by the Cal/Nev #CreditUnion Leagues
8 hours ago
.@growfinancial's #salsa sensation spices up seed giveaway #NewsNow
9 hours ago
.@TheNCUA Office of Small CU Initiatives soon--maybe Nov.--will launch website for #CUs 2 research #creditunion vendors or service providers
9 hours ago
.@TheNCUA says late 2Q Call Report filers 2 pay total of $17,111 in penalties.Individual penalty range is $52 to $1,824;median is $256. 2of2
9 hours ago