Reltio Matching

Reltio Matching

Matching is the process of identifying records that are identical or related to one another. Typically, when considering matching data in a master data management system, we think about finding data that is completely identical. When such data is found, it is unnecessary to keep both sets of data. One of the features of Reltio MDM is that you can find these identical records easily, and also find records that are related. 

Reltio provides two primary matching methodologies:

  1. Rule-Based Matching: This method relies on user-defined rules to instruct the platform on how to identify matching records. It offers precise control over the matching process.

  2. AI-Powered FERN (Flexible Entity Resolution Network) Matching: Reltio's FERN leverages advanced machine learning, including industry-specific pre-trained models and database vectorization, to achieve superior data unification. Notably, FERN utilizes Large Language Models (LLMs), enabling zero-shot matching without the need for model training or tuning. Its semantic understanding of data facilitates the discovery of unique matches, and it provides out-of-the-box transliteration for 60 languages.

Furthermore, Reltio allows for a hybrid matching approach, enabling the simultaneous execution of both rule-based and FERN matching methods.


Learn more 

The Rule-Based Matching Process

Rule-based matching is based on instruction, which means the configuration provides the instruction and Reltio executes the matching dictated by those instructions. Then, Reltio merges these records either automatically or create a suspect match for the data stewards to review and resolve manually.

Read it Here

Transform Your Data Matching with Reltio's AI/ML-Powered FERN: 

Dive deep into the future of data matching with Reltio's innovative AI/ML-powered Flexible Entity Resolution Network (FERN). In our latest Community Show, Principal Product Manager Suchen Chodankar reveals how FERN leverages Large Language Models (LLMs) to revolutionize data unification and streamline the entity resolution process.

Overcoming Traditional Challenges

Traditional rule-based entity resolution systems often struggle with accuracy, leading to false positives and significant manual data stewardship. FERN addresses these issues head-on by automating high-accuracy, real-time matching with pre-trained models, significantly reducing the need for manual intervention


Unraveling the Merge Introducing Auto Unmerge for Accurate Data Records

Reltio's automatic unmerge feature streamlines the process of separating previously merged entity records when discrepancies or changes in data are detected. Designed for data stewards and technical leaders, this feature automatically unmerges consolidated records triggered by CRUD (Create, Read, Update, Delete) events that alter attribute values on contributing source data crosswalks. For example, if a first name changes from "John" to "Jack" in the source data, making the profiles no longer match, the system will automatically unmerge these profiles. The feature is not applicable when using contributors or data providers during data loading processes or when integrating with Salesforce or third-party data enrichment services.

Organizations can enable automatic unmerge at the EntityTypes level, allowing selective unmerge actions based on specific needs. They can also configure rules to retain certain merges and avoid unnecessary unmerging and merging cycles. Automatic unmerge does not apply to manually merged records unless explicitly configured to do so, preserving manual interventions by data stewards unless specified otherwise. For changes in match rules or survivorship strategies, a BatchUnmergeEntities API must be executed to impact the specified entity types. This feature enhances data management efficiency by ensuring real-time data accuracy and reducing the need for manual unmerge actions.

In this video, we're talking all things Matching and Merging. Reltio former community program manager, Chris Detzel, and Reltio technical consultant, Joel Snipes, discuss match rule features, design and tuning in order to get the most out of your data. This session explores what makes a good merge rule, what makes a good potential match, and shows some of the common pitfalls new MDM practitioners fall into.


In this session, Suchen Chodankar, Reltio Product Manager, covers how different components of Reltio's matching engine such as tokenizer, comparators, and relevance score calculation work together to generate the matching result. Suchen also talks about the anatomy of the match rule and how various properties of the match rule configuration can influence the matching results.


Blogs on this Topic

Discussions on this Topic

  • matchFieldURIs & keyAttributeURIs

    Discussion

    Hi Community Members, This post is regarding short detailing of What is matchFieldURIs & keyAttributeURIs Usage of matchFieldURIs & keyAttributeURIs Short summary of where matchFieldURIs & keyAttributeURIs ...

Still can't find what you're looking for? 

Login to the Reltio Community to ask a question.

Search the Reltio Community