Introduction

ATS is a modern algorithm system used by hiring managers and companies to streamline their hiring process. This algorithm is used to filter out resumes and track applicant data according to job requirements. Job seekers pursue to optimize their resume to be ATS-friendly for the best outcomes. However, many applicants lack effective resume parser tools that can

• Extract their relevant experiences

• Provide reliable and applicable feedback

• Effectively alter their resume for specific job descriptions

  
  

By addressing these concerns regarding ATS from a job seeker perspective, Resume Parser aims to establish a friendly, reliable, and effective AI resume parser web browser tool.

Project Duration

Jan 2024 - Jun 2024 | 20 weeks

Team

5 Developers, 2 Designers, 1 PM & 1 Team Mentor

Completed at CodeLab, a professional software development and UX / UI agency at UC Davis.

Role

UX Designer

UX Researcher

Product Designer

Tools

Figma

Airtable

Google Suite

Slack

Jira

Research

Market Research

Market research was conducted to gain an understanding and knowledge about ATS and its prevalence/significance in the market. We found that:

• When applicants utilize ATS-friendly resumes, their chances of the resume being recognized in the application process are significantly higher compared to ATS standards

• The tech industry is one of the top industries taking the most advantage of the resume parsing algorithm

• 99% of Fortune 500 companies utilize ATS

Competitive Analysis

I compiled a spreadsheet comparing three resume parsers on the internet. Their overall product features were compared to gain an insight into what features are beneficial for users.

Key findings include:

• Resume parsing is mainly split into two categories — parsing based on content-specific information, and parsing based on formatting.

• Vertical page division is efficient for home and landing pages, while horizontal page division provides additional information displayed during feedback of a parser.

• A consistent color theme, clear buttons, and whitespace leads to an intuitive, user-friendly visual interface and adds to product branding.

User Survey

• 42+ responses to a survey consisting of 19 questions, mixed multiple choice and open-ended questions

• 69% of users most value tailoring resume to a specific job description

• 57% of users expect resume to parse for repetition, word impact, phrasing, action words, and conciseness

Ideate

User Stories

• High Priority: see immediate visible results, gain feedback on whole resume, choose type of feedback I want to focus on first, be able to tailor resume to job descriptions

• Medium Priority: see past uploaded resumes

• Low Priority: upload multiple resumes at once

Wireframing

Iterations

Design System

Prototypes

Detailed Pages and Features

• Feedback Choice: A side-by-side comparison of feedback, based on semantics of the resume vs. syntax of the resume.

• Detailed feedback sections: The Content Feedback page shows specific feedback categories, diving deeper into the type of revisions made.

• Dashboard: Contains statistics about career matches based on resume, job recommendations, organized to-do list for user, and scores based on parsability.

Conclusion

What I would do differently if I had more time:

1. Conduct more user-testing on key pages

   • Only able to conduct user-testing on landing page and sign up pages due to time constraints

   • Larger pool of qualitative user-testing would be beneficial

2. Further explore boundaries for incorporating job specific tailoring

   • Incorporating idea / feature of giving user the choice to pick between having their resume be tailored to job description, and having resume just be parsed without tailoring

   
   

3. Expand on AI capabilities for this project

   • Creating a new starter AI resume instead of uploading existing one — having an AI-generated resume based on a specific job description

   • Recommending job posts based on the uploaded resume