During clerical review for a match and merge solution, a data steward could face thousands of records that must be either merged or rejected. The machine learning matching agent (MLMA) eases the workload by providing recommendations for merging or rejecting based on the data steward's decisions.
The machine learning engine is part of Stibo Systems' ASPiRE cloud environment. The MLMA analyzes and learns from the data steward's decisions within the clerical review task list. After the data steward meets the threshold of decisions, the matching agent provides merge and reject recommendations within the clerical review task list, which the data steward can either heed or disregard.
Solution Overview
The matching event processor updates new tasks and changed tasks with a new merge / reject recommendation. This happens when an enabled matching agent exists that has successfully completed the training process.
The MLMA functionality is in the ramp-up phase and is only accessible through an early adopter program. As part of this program, Stibo Systems will provide a client ID and passphrase, which are needed to configure the authentication REST gateway. To learn more about the ramp-up phase / status, see the License and Component Lifecycle topic in the System Release and Patch Notes section of online help here. To participate in the early adopter program, send an email request to SYSClericalReviewMatchingAgent@StiboSystems.com.
The following topics outline the setup and function of the MLMA:
-
Configuring MLMA (here)
-
Maintaining the MLMA Data Model (here)
-
Matching Agents (here)
-
Adding MLMA Recommendations to a Clerical Review Task (here)
ASPiRE License
ASPiRE uses the Dedupe library with an MIT license.