Get Started

Resource Center

You'll find useful information about our software here in the resource library. Explore technical specifications, helpful videos, case studies and frequently asked questions.

Technical Specification

AI Matching Engine

Sovren has the most robust AI matching engine because we’ve...

Technical Specification

Job Order and Resume Parsers

We’ve listed out the technical specifications for our job and...

Case Study

A top executive recruiter puts accuracy to the ultimate test.

Due to a confidentiality agreement, we can’t reveal the name of this customer, but we can share that they are...

Case Study

Vertifi Ltd. put Sovren to the test – and we were measurably faster and more accurate than the competition.

Vertifi Ltd. is a UK-based recruitment technology provider that uses a unique brand of CV Exchange technology known as “iProfile”...


Career Path Recognition

Like a recruiter, our engine assigns the highest scores to candidates whose current career path aligns with a job. It recognizes that while a candidate may fit a job’s qualifications, they can still be a poor match if their career has deviated from the role.


True Absolute Scores

Other engines will report a poor match as “100%” just because it’s the best available. Our engine reports absolute scores, so each match is reported as its true score from 0-100. We also provide sub-scores on different categories of data, so you can see the reasoning behind the score.


Configurable Per Transaction

Want to accommodate different parsing needs for each customer and every transaction? Consider it done. Enable or disable any of the sub-parsers (like patents and security clearances) for each job order, resume or CV parsing transaction.


Insightful Candidate Summaries

Don’t read between the lines — our resume parser will. It extracts and calculates helpful details from data like primary skill set, highest management level and time spent in the workforce. Review individual data points or a human-readable summary of each candidate.


Holistic Profile Matching

You know each candidate is more than a list of keywords — and so does our AI Matching Engine. It matches based on a holistic profile, assigning context, time values and meaning to all the data on candidates’ resumes.


Unmatched Speed

Expect average parsing times of about 500 ms per transaction (5–20x faster than our competitors). Run many transactions simultaneously for an even greater throughput. Need to parse 1,000,000 resumes before lunch? You can.


Teachable Matching Criteria

You decide exactly how our AI matching engine thinks about each individual transaction. It will find, rank and sort the best matches according to your criteria.


Supports Every Source

Parse a resume or a job order in any source format, including LinkedIn profiles and any other job board format.


Transparent Match Explanations

An intelligent engine should be able to intelligently explain its results, but none do — until now. Not only does it deliver the best matches — it tells you how and why it produced them and offers tips to improve the results. Welcome to the future.


Multi-directional Matching

Match in whichever direction you want — match resumes to relevant jobs or to similar candidates. Use jobs to find a candidate or to find similar jobs. The choice is yours.

A resume/CV parser is used within human resource software and on recruitment websites, job boards and portals to simplify and accelerate the application process. It does so by extracting and classifying thousands of attributes about the candidate and providing a foundation for the semantic searching of candidate data. The parser identifies hundreds of different kinds of information within a resume or CV and clearly tags each data point (for example: first name, last name, street address, city, educational degrees, employers, skills, etc.). The results may be outputted in HR-XML or JSON format. Sovren has been building this technology for over two decades.

No, Sovren is the fastest, most accurate, and most configurable parser available anywhere.

On average, about 500 milliseconds.

Essentially any non-image resume and CV format, including all of the popular job board formats and social and professional networks.

No, the Sovren resume parsing SaaS does not store any resumes.

Yes, you can use the built-in skills list, or customize a skills list with IDs that correspond directly to your system.

Yes, you can normalize company names, position titles, school names and degree types.

There are multiple output options (HR-XML, JSON, TEXT, HTML, RTF, Template).

No, the parser has auto language detection so you will never have to tell the parser what language a CV is written in.

Yes, the parser constructs a summary of who the candidate is today, a management summary, as well as average time at each employer and more.

  • Take a moment to read the entire API Documentation. This will help you understand in detail how to implement the service and what results to expect.
  • Download a sample application (available in the API Documentation page) that best suits your programming language expertise.
  • Run the sample application (entering your SaaS credentials) and start parsing away.

You should check your remaining credit balance by looking at the CreditsRemaining field in the ParseResumeResponse or ParseJobOrderResponse object after each resume or job order parse (respectively). You can also call GetAccountInfo at any time to get this information (see the API documentation for more information).

To accurately test resume parsing, please follow these rules (read Best Practices to Test Resume Parsing Software for a more in-depth look at each of these rules):

  1. IMPORTANT: Do not use resumes with fake data such as Company1; Anytown, USA; 713-555-5555. The parser very smartly ignores all such fake data.
  2. Never accept vendor-supplied resumes.
  3. Test only about 30-50 resumes per language or locale.
  4. Don't test resumes from just one source or industry or job type.
  5. Evaluate results by hand, comparing to the actual resume.
  6. Don't just test for accuracy, test for completeness.
  7. Test scalability and robustness.
  8. Test with multiple configurations.

See how do I accurately test resume parsing above and make sure you are following each of the rules for accurately testing resume parsing.

Look at the ConvertedText: Resumes that may seem very clear when looking at the original file may yield unexpected results. In many cases, this is due to the conversion from the original file format to plain text format. The most common issues are:

  • PDF documents
  • MS Word Templates
  • Images (e.g., scanned resumes)

If you are parsing a PDF document and see jumbled text, it may be corrupted. To verify this, open the file with Adobe Reader, then choose File => Save As Other => (.txt). Look at that extracted text and if it appears jumbled, then the PDF is corrupted and there is nothing that can be done with this file (see Problems With PDF Format).

Check the Parser Configuration: The parser has many settings that may be turned on or off, all of which affect the parsing results. For example, some sections such as Training are not parsed by default but you can choose to parse for this by setting the ParseTraining flag to true.

If you are parsing a foreign language resume (e.g. Chinese) and seeing values in your saved HR-XML such as "????", this means the file was parsed correctly but you have handled the reading/saving of the response incorrectly. The problem is in how you (or your SOAP library) are reading or processing the HTTP response content. The response is UTF-8 encoded, but you are reading it (or transforming it or saving it) with an ASCII or ANSI encoding somewhere along the way.

Read through Sovren's Tips for Electronic Resumes for more helpful tips.

Email and be sure to include:

  • The original resume.
  • The ConvertedText.
  • The HR-XML output from the Parser.
  • A detailed explanation that specifically describes the problem.