Skip to main content
Sign in

Required Skills and Preferred Skills in JD Parsing?

RChilli Support
  • Updated

In RChilli's JD (Job Description) Parsing, skills are categorized into two types: Required Skills and Preferred Skills. These categories help structure job descriptions in a way that enhances candidate-job matching through semantic understanding and taxonomy enrichment.

What Are "Required Skills" and "Preferred Skills"?

1. Required Skills

These are the must-have qualifications or abilities that a candidate must possess to be considered for the role. They typically include:

  • Core technical abilities (e.g., Java, Python, SQL)

  • Certifications (e.g., PMP, AWS Certified)

  • Educational qualifications (e.g., Bachelor’s in Computer Science)

  • Years of experience in a domain or role

RChilli's JD Parser identifies and segregates these from the JD text using its AI/ML engine and taxonomy-based classification. They are essential for precise filtering and scoring in matching APIs.

2. Preferred Skills

These are nice-to-have competencies that enhance a candidate’s profile but are not mandatory. These could be:

  • Secondary tools or technologies (e.g., Tableau, Jenkins)

  • Soft skills (e.g., leadership, communication)

  • Industry-specific knowledge or languages

  • Additional certifications or courses

Preferred skills help fine-tune candidate recommendations and are used for more nuanced scoring and ranking when matching resumes to jobs.

How Does RChilli JD Parser Identify These?

RChilli uses a combination of:

  • Natural Language Processing (NLP) to extract skills from context

  • Taxonomy 3.0 to tag skills and categorize them accurately

  • Job zoning logic to determine sections like job responsibilities vs. qualifications

The skills are output in structured JSON under separate nodes for:

  • RequiredSkills

  • PreferredSkills

This output structure supports downstream APIs such as Search & Match, which use these fields for relevance-based scoring.

Use Cases for Skill Segregation

  • ATS Filtering: Prioritize candidates based on strict qualification filters.

  • Matching Accuracy: Assign different weights to required vs. preferred skills.

  • Bias Reduction: Enable blind matching based on skills and not personal identifiers.

  • Automation: Map extracted skills to job templates or workflows in ERP platforms like Oracle or SAP.

Reference & Further Reading

Related articles

Comments

0 comments

Please sign in to leave a comment.