Offline. On Target.
The Data Clustering Engine (DCE) is an offline, high quality data grouping and investigation engine for all forms of identification data. Clustering is the process of analyzing and grouping diverse data records into “clusters” of similar or related records.
Examples of Clustering Projects Include:
- Creating a "consolidated customer view" using data sourced from disparate systems (for example, using the criteria "believed to be the same name, address and ID Number") despite the variation in the data
- Grouping a collection of separately sourced "prospect" records by "household" or "delivery point"
- Screening a "marketing list" file against the "customer" file and a “do not mail” file to discover which records should be eliminated
- Grouping Sales Tax registrations with Yellow Pages information to see who is not paying sales tax
- Grouping all the records in a database that could be related to a known fraudulent transaction
- Grouping all of the incident records in a criminal intelligence database, around known groups of criminals or criminal activity
The different forms of clustering and its different objectives are achieved by using different clustering rules. For example, a fraud application may use very different membership criteria to group two records than a marketing campaign application.
DCE achieves all this without requiring additional programming. It can be run in stand-alone mode or as part of another process. Rules can be quickly selected and modified using the DCE console. DCE is powerful enough to be run against enormous volumes of data, accurate enough to handle high-risk projects and designed to fit into almost any environment.
For more information, please see our brochures, whitepapers and presentations, our customer success stories, or contact us directly.
