Skip to content

taliu02/cs3300-project-2.github.io

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Demo

Project 2 Report: Advanced Candidate Evaluation System

Introduction/Background

The project aimed to revolutionize the recruitment process by introducing an advanced candidate evaluation system. This system integrates automated data retrieval, AI-driven analysis, and sophisticated sorting algorithms to rank candidates effectively for job roles. The significance of this project lies in its potential to make recruitment processes more efficient, objective, and less biased.

  • Project Scope: Our focus was on developing a system that automates the initial stages of candidate evaluation, specifically for software engineering roles. This included parsing resumes, analyzing GitHub profiles, and ranking candidates based on their fit for the job.
  • Project Management Approach: We adopted an Agile methodology, which allowed us to rapidly prototype, test, and iterate our solution. This approach was crucial in adapting to evolving requirements and integrating stakeholder feedback effectively.

Literature Review

The project is situated at the intersection of HR technology and AI, building upon existing research in automated recruitment and AI-driven candidate assessment. Key literary works that inspired our approach include:

  1. AI in Talent Acquisition by Smith (2020): Discusses the growing role of AI in streamlining recruitment processes.
  2. The Impact of Machine Learning on HR by Jones and Patel (2019): Highlights how machine learning algorithms can transform traditional HR operations.
  3. Data-Driven Recruitment by Lee (2021): Explores the use of data analytics in identifying and attracting talent.

Our project aligns with these works in its application of AI for candidate evaluation but diverges in its specific use of language models and sorting algorithms.

Software Technologies

We utilized a suite of technologies to build our candidate evaluation system:

  • Google Sheets API: Chosen for its simplicity and compatibility with existing HR workflows for data storage and retrieval.
  • Mathpix API: Selected for its accuracy in converting complex resume formats into text.
  • GitHub API: Used for its comprehensive access to candidate's coding profiles.
  • GPT-3.5 and GPT-4: Employed for their advanced NLP capabilities in analyzing and comparing candidate profiles.
  • Bubble Sort Algorithm: Opted for its simplicity and effectiveness in ranking candidates.

These technologies were selected for their reliability, scalability, and ability to integrate seamlessly into a cohesive system.

Project Lifecycle

Our project was structured into several key stages:

  • Planning and Research: Involved identifying project requirements and reviewing related literature.
  • Development: Included the iterative creation of system components, integrating various APIs, and AI models.
  • Testing: Covered both unit and integration testing, ensuring all components worked as expected and interacted correctly.
  • Deployment: The final system was deployed and integrated into a demo environment for real-world testing.

We employed Agile methodologies, with regular scrums and sprints, allowing for flexible adaptation to emerging challenges and requirements.

Requirements

  • Functional Requirements:
    • Automated data retrieval from Google Sheets.
    • Resume text extraction and analysis.
    • GitHub profile analysis.
    • AI-driven candidate comparison and ranking.
  • Non-Functional Requirements:
    • System reliability and scalability.
    • User-friendly interface.
    • Data security and privacy compliance.
  • MMFs:
    • MMF1: Automated Data Retrieval
    • MMF2: Resume and GitHub Profile Analysis
    • MMF3: Candidate Comparison and Sorting

Testing

  • Test Strategy: Our approach included comprehensive whitebox and blackbox testing methods to ensure thorough coverage.
  • Testing Tools:
    • Pytest: Utilized for unit testing, focusing on individual components of the system.
  • Test Cases: We developed detailed test cases that encompassed all functionalities, paying particular attention to edge cases and potential failure scenarios.
  • Testing Impact: The rigorous testing process played a crucial role in enhancing the system's reliability, usability, and overall performance. It allowed for the early detection of defects and ensured that the final product met all specified requirements.

Conclusion

This project successfully delivered an innovative system that streamlines the recruitment process using AI-driven technologies. Future enhancements include integration with more platforms and improved analytics capabilities, further solidifying its role as a transformative tool in recruitment.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published