Find Similar Contacts leverages Beamery’s AI-powered matching engine to allow you to easily find and review relevant candidates based on a single profile, minimizing the manual work of sourcing and giving you more time to make meaningful connections with the best candidates.
Find Similar Contacts and Suggested Contacts both leverage Beamery's AI-powered matching engine. To understand. To understand the difference between these features and when to use each feature, check out this article.
How does Find Similar Contacts work?
AI can be mysterious and sometimes hard to trust, but it doesn’t have to be this way. In this article, you’ll learn what to know about Find Similar Contacts so you can have confidence in the AI behind this powerful feature.
When you click on Find Similar Contacts on any Beamery profile, the AI will analyse the profile’s location, job titles, languages, skills and keywords found in profile attachments. Each of these areas of the profile is given equal weighting by the AI analysis.
Then, Find Similar Contacts will assess all the contacts in your database to find other profiles that look just like it. Each contact is given a ‘Match Score’ showing how similar they are to your chosen contact. The top 20 matching contacts are presented for you to review and take action.
How does the Match Score work?
Find Similar Contacts provides a Match Score on each similar contact to show you how closely they match your chosen profile. The similar contacts are shown in Match Score order with the best matched contacts at the top. The Match Score is calculated and used only behind the scenes of Find Similar Contacts, so you will not see a numeric ‘score’ associated with a candidate profile.
The 20 most similar contacts in your database will be shown in the list of similar contacts, ranked by Match Score. In the example below, Christopher Talbot is the contact with the strongest Match Score in the CRM for this initial profile, so this profile is shown at the top of the list, with a full green bar in the Match Score column. In comparison with Christopher Talbot, Mark Hernandez does not match as strongly with the initial profile, so his Match Score is shown as a partially filled yellow bar.
The keyword terms on each similar profile that match those on the profile you started with are shown on the grid, so that you can understand at a glance which terms are generating the match score. You can further dig into a contact’s profile and their similarity to the initial profile by opening the mini-profile and reviewing their profile information.
What profile information will Find Similar Contacts use to determine the ideal persona and match score?
Find Similar Contacts analyzes candidate location data in two ways, using map coordinates associated with geolocation data, and by matching text strings of relevant address, city and country data. These methods are used in combination to show similar contacts to you.
Using geolocation data, Find Similar Contacts finds the latitude and longitude position of your initial contact. It then draws a circle from that point and allocates a higher Match Score to those within the area. Contacts outside the area are not excluded, but are given a lower score.
When matching location keywords, Find Similar Contacts analyzes the words and phrases in the location field of your initial profile. Significant combinations of terms are recognized and given greater emphasis. For example, if your initial profile has “United Kingdom” in their location, then other profiles on which that term appears in the location field will have a higher match score for location.
This same type of matching is carried out for addresses, cities, and countries to be sure the similar contact suggestions you receive are as geographically relevant as possible.
When Find Similar Contacts analyzes the job titles of contacts in an initial profile, it assesses the frequency of significant words in those job titles. For example, if an initial profile has four job titles in their experience section with the word ‘designer’ in their job title, ‘designer’ would be ranked highly, and other profiles that also heavily feature the word ‘designer’ in the profile will have a higher match score for job titles.
So, when generating similar contacts, the frequency of a significant word in job titles affects how high the Match Score is for a contact’s job titles. In the previous example of ‘designer’ being added to the ideal persona, a profile with five different roles that include the word ‘designer’ would have a higher match score for job title than a profile with only one role containing the word ‘designer’.
Find Similar Contacts will also analyze how common a word from a job title is in all contacts in the CRM. If a word is particularly rare, this will be given more significance, and contacts who have job titles that include this word will have higher match scores for job title.
When Find Similar Contacts analyzes the languages on the initial profile, it assesses which languages are present on the profile. Then, when Find Similar Contacts looks for contacts to suggest, those who have the languages in common with the initial profile would have a high match score for Languages.
When analyzing attachment keywords, Find Similar Contacts uses the analysis already carried out on job titles. Then it will return the contacts that have attachment data which best matches the attachment keywords from the initial profile.
How Can I Improve the Similar Contacts I See for a Profile?
Good data always leads to better quality results. Now that you know which areas of the profile contribute to the AI matching carried out by Find Similar Contacts, you should ensure that the profile you are using as the initial profile has robust information. A job title, a location and an attachment is a great start.
Adding information to the areas of the profile covered in this article will give the AI more information to work with, and will improve the quality of the similar contacts that you receive.
The other factor that will contribute to the value you get from similar contacts is the data quality of contacts across your CRM. If new candidates are added to your CRM who have similar profiles to your initial profile, you will see these appear in your list of suggested similar profiles.