Affinda’s Resume Parser uses recent advancements in AI technology to extract CVs in 56 languages while being able to recognize and process over 100 different fields. Although younger than more established competitors, independent testing has confirmed our product as the most accurate Resume Parser on the market.

The Affinda Resume Parser is built on top of our AI Engine, VEGA, which brings to market innovations in NLP (Natural Language Processing), Transfer Learning, and Computer Vision that enable us to understand documents like a human and return structured data from resumes typically within 1 – 2 seconds.

How to use Affinda's Resume Parser?

Typically, customers will use our REST API to parse resumes. Simply post a resume to the API and we will return the extracted data in a JSON file. Resume data can be uploaded in three formats:

File upload - upload a PDF, DOC, DOCX, TXT, RTF, HTML, PNG, JPG,
URL - post the URL containing a resume file
Data upload - upload resume data directly without parsing any resume file by providing a JSON-encoded string (note, this method will not impact your parsing credits)

Further information about how to use our API and client libraries is available here.

Users can also upload documents, extract data, and export results from the Affinda web app.

Data extracted

Affinda can return over 100 data fields from resumes. These data fields include:

Personal details
Title, first name, middle name, last name, address, contact phone, email, websites, date of birth, headshot, LinkedIn profile

Work experience
Employer, job title, location, dates employed, total years experience, occupation classification, management level

Education
Institution, degree, degree type, accreditation, year graduated

Certifications
Courses, diplomas, certificates, security clearance, and more

Skills
Individual skills (mapped to a detailed best-in-class taxonomy containing over 3,000 soft and hard skills), skill type, number of months using skills

Language(s)
Language(s) spoken, the language of the resume

Summary
Candidate summary and objective, section raw text, the probability the document is a resume

Referee details

Name, phone number