Summary
Within the Customer MDM solution, a new Machine Learning Matcher has been created for STEP SaaS environments which enhances the capability to establish accurate matching algorithms by providing a pre-trained machine learning model for comparing person names.
Details
With the 2024.1 update, the matching setup has been simplified exclusively for STEP SaaS environments as Stibo Systems introduces the first Machine Learning Matcher which enhances the capability to establish accurate matching algorithms more quickly.
The Machine Learning Matcher improves the ability to create accurate matching algorithms by providing a pre-trained machine learning model designed for comparing person names. Additionally, the Machine Learning Matcher for person names supports groups of nicknames, further improving the accuracy of the scores and simplifying the process of defining the nickname aliases.
Subsequent model version updates will expand support to include additional individual and organizational party data elements, such as addresses, emails, and phone numbers. The pre-trained machine learning models provide substantially more accurate scores than the existing matchers that are based on static algorithms.
For more information, refer to the Matcher: Machine Learning Matcher topic within the Matching, Linking, and Merging documentation.
Explore further by clicking the video below. If it does not play as expected, it is also available in the Customer / Partner Communities and may also be accessible within Stibo Systems Service Portal.