Deterministic matching is a technique used to find an exact match between records. It involves processing data from various sources, such as online purchases, registration forms, and social media platforms. This method is ideal for situations where the registry contains a unique identifier, like a social security number (SSN), national identification, or other identification number. However, when it is not possible to determine a unique identifier or other data about a person (address, telephone number, email address, etc.), deterministic matching may be less reliable.
This leads us to probabilistic coincidence or “fuzzy coincidence”. Probabilistic identity resolution refers to the use of predictive algorithms to find the probability that two records belong to the same individual. This technique is used when no field can provide a reliable match between two records. Other CDPs also use deterministic data (unique identifiers, such as email addresses and phone numbers), but will need access to both deterministic and probabilistic data to resolve the customer's identity and create a complete customer profile.
Identity resolution is the process of attributing all of a customer's behavior to a single, unified customer profile. Probabilistic matching involves comparing several field values between two records and assigning each field a weight that indicates the extent to which the two field values match. The creation of profiles will not only show the accuracy of certain fields in terms of their content, but also which anonymous values (or equivalences) can easily match in different sources when analyzing duplicate records. Specifically, probabilistic methodologies can add value and scalability when applied within an identity solution that has a basic deterministic basis.
Deterministic matching is the process of identifying and combining two different records from the same customer when an exact match is found in a unique identifier, such as the customer ID, Facebook ID, or email address. Best-in-class identity solutions should be based primarily on a deterministic human-based basis. This campaign is not as specific as others, so the cost of misidentification is much lower and the potential benefits of recognizing more people on all channels and devices are potentially enormous. While a relatively simple concept, identity resolution is difficult to implement in practice due to the number of potential customer touchpoints, both online and offline.