Skip to main
Group 15


Matching that is diverse by design

Sovren's AI Matching Engine understands candidates as humans with career profiles — not just a string of keywords. We've modeled our engine to think like a recruiter and we never store personal data (PII), which means that bias is completely removed from both the algorithms and from recruiters' viewing of the anonymized data. The objective facts of the resume are scored against the objective facts of the job so an objective, explainable comparison is made.
Candidate 1 Picture
Software Developer
3 Years Experience
Candidate 2 Picture
5 Years Experience
Candidate 3 Picture
General Contractor
17 Years Experience
Candidate 4 Picture
Physician Assistant
11 Years Experience
Group 23

Controllable Matching

Our AI Matching Engine is the only human controllable engine on the market. Don't like the matches? No problem! You are in charge: tell the engine what is important to you, then rerun the match and the engine will return the results that were matched and scored your way. You are in complete control and you get to decide how it thinks. The engine works for you.

Bimetric Scoring

Our matching software has the world's first two-way matching algorithm which looks at how well the person and job fit each other. Our engine knows that you can be a 100% fit for a lifeguard job, but a lifeguard job is a terrible fit for who you are today. We examine BOTH directions of fit, and score accordingly. We look at the data that is most relevant and important for who you are, not who you used to be.

White Box AI

Our AI is based on facts and science and is transparent throughout the process. Our software can tell you exactly how it arrived at each score: what matched, what didn't match, and the importance of each type of data. Our scoring is fully transparent and broken down by category and by each datapoint within a category. We have the world's only white box AI for recruiting.

Seamless API Integration

Our job order and resume parsing API make integration easy and straightforward through REST/JSON. We also have official, open-source SDKs available in several languages that allow you to get started with as little as 3 lines of code.
* Education
* EmploymentHistory
* SkillsData
SovrenClient client = new SovrenClient("123456", "abcdefghij", DataCenter.US);
Document document = new Document("resume.docx");
ParseRequest request = new ParseRequest(doc, new ParseOptions());
ParseResumeResponse response = await client.ParseResume(request);
    "ContactInformation": {
        "CandidateName": {
                "FormattedName": "Molly A. Adams",
                . . . ,
        "Telephones": {
                "Raw": "(678) 555-1212 x 180",
Other products have reasonably good match results, but Sovren can do it all with unmatched speed.
Alex MacKenzie
Vice President - ProCom
Group 15
Group 15
Client quote author
01 / 03

Frequently Asked Questions And Use Cases

Frequently Asked QuestionsFAQsMatching Use CasesUse Cases
Matching is a fully automated process. You give the engine a document (a job or a resume) and tell it to bring you back the best matches (jobs or resumes). The engine determines the relevant criteria and returns the best candidates. Matching allows for humans to tell the engine what types of data are important using category weights while still letting Sovren do the heavy lifting of generating the queries and scoring the results.

Searching uses a human-specified query. The recruiter tells the engine exactly what she wants, and the engine brings back documents that match those specific criteria.

Bimetric scoring is both a feature and a product. Bimetric scoring as a feature is the process by which our matching engine looks at two directions of fit, such as (1) how well does the candidate fit the job? (2) how well does the job fit the candidate? Bimetric scoring as a product is used to score a user-determined set of documents. For example, using the Bimetric Scoring product, you can see exactly how a set of 50 applicants for a job score against that job.
No, because that is a terrible practice! Our engine doesn't learn based on your recruiter's clicks because there is no way to know why the user clicked on a profile to review, or what they really thought about what they saw. Systems that "learn" from recruiter clicks quickly go off the rails as the system "learns" from poor-performers and makes invalid assumptions about intentions. Our algorithms are curated by our team of experts and are explainable down to each detail.
Parsed documents that have been sent to the API to be indexed are scrubbed of ALL personal data and personally identifiable information (PII) and then stored in the specified index. This security measure also assists in removing bias from the recruiting process. If you want to simply search for a candidate by name, use your own database.
Yes. You can index a wide variety of data that you define and that you use in narrowing or widening result sets.
You can test bimetric scoring, the same algorithm used in matching, on our demo site. To test matching at scale, reach out to to discuss setting up a test environment using real data.
View all FAQsCTA Arrow
Ready to get started?

Sovren Accelerator Program

Parse, index, search, and enrich up to 5000 documents for $200
This is a great way to get started with Sovren. The accelerator program gives you full access to our parsing software and allows you to test our AI Matching and Data Enrichment APIs as well. This is a one-time purchase worth up to a $1000 value.
Group 23Unlimited matching transactions.*
Group 23Unlimited boolean text searching.*
Group 23Integration consulting services and support.
Group 23Full access to JAVA and .NET SDKs.
*All subject to the Acceptable Use Policy