Principle Based Entity Resolution

It's time to break away from the rules.

Most entity resolution methods utilize inflexible rules that are limited in scope. Senzing® entity resolution operates on principles – generalized knowledge based on the expected behaviors of entity attributes (names, addresses and identifiers). For example, social security numbers (SSNs) typically point to only one person, but dates of birth (DOBs) are shared by many people.

Senzing® software is a real time AI purpose-built for entity resolution that combines machine-learned domain-specific knowledge and real time learning to determine when entities are the same, possibly the same, related or possibly related. Principle based entity resolution makes Senzing software easier to deploy and virtually eliminates the need for pre-training, tuning or experts. The differences between rules and principles are distinct.

How Are Principles Different (and Better) Than Rules?

You tell your child to stop throwing rocks at cars, which is a rule. The next day, you find him throwing baseballs at SUVs and have to tell him not to do that, too, another rule. A few days later, you have to tell him not to throw golf balls at trucks, fire engines and ambulances, more rules. Instead of all these rules, you just need one simple principle: Don’t throw things at other people’s stuff.

Senzing Principle Based Entity Resolution Delivers

Faster time to value due to ease of ingesting data sources

Lower costs due to no need for tuning, training or experts

More accurate and explainable record matching

Senzing Principle Based Entity Resolution Functionality

Our methodology assigns three behaviors to each entity attribute:

Frequency

How many entities share the same value? For example, a social security number (SSN) is commonly used by only one entity, an address is shared by a few, and a date of birth (DOB) is shared by many.

Exclusivity

Does an entity typically have one type of value? That is, should an entity have only one value for an attribute, such as with an SSN or DOB, or can the entity have more than one value, such as with credit card numbers?

Stability

Is the value constant over an entity’s lifetime? For example, an entity’s SSN and DOB are typically stable, while a home address is likely to change.

Senzing software comes preconfigured with the attributes and expected behaviors of people and organizations, so you can load and resolve entity data without configuration, training or tuning. Senzing principles are applicable across a wide range of entity types with minimal adjustments.

Senzing principle based entity resolution is easier to deploy and use than other entity resolution methods and requires no pre-training, tuning or experts.

SCHEDULE A DEMO