Large Language Models Bankathon 1.0

Overview

The LLM-based application simplifies and improves HR processes by using Language, Logic, and Machine Learning. It leverages Natural Language Processing, machine learning, and analytics to enhance efficiency, effectiveness, and decision-making in HR operations.

This user-friendly, scalable, and customizable application integrates with existing HR systems and tools, ensuring smooth data flow and compatibility. Its ultimate goal is to optimize HR processes, minimize manual efforts, enhance decision-making, and improve the employee experience.

Tech stack

• Open to all
• Must use a Large language model for the given problem

Task 

• Input: Accept job description and multiple CVs in various formats.
• Job Description evaluation
• Score the job description based on the job title, and provide recommendations for enhancements
• Give the user the option to either continue with the original version or incorporate the suggested changes
• CV ranking
• Rank the CVs according to their alignment with the job requirements and shortlist candidates
• Provide additional information on the shortlisted candidates
• Email notifications: Send emails to the shortlisted candidates, informing them about the next steps in the hiring process
• Screening questions
  Develop screening questions for each candidate, considering different levels of importance or significance assigned to the job description and the candidate's CV
• First-round interview
• Conduct the first-round of interview
• Record the candidate's responses to the screening questions
• Evaluate their performance for consideration in the next in-person round
• Communication
• Maintain continuous communication with the HR team
• Providing updates on the hiring process and relevant information throughout

Submission format 

• Source code in zip file
• Dataset used
• Demo video of the project
• Important files, PDF, resources used and ppt

Resources

• LLMs in HR analytics: how it helps HR make better decisions
• LangChain Documentation
• Open AI Models

Evaluation metrics

• User Interface (UI) Design and Information Extraction (10 points)
• Quality of the UI design, including but not limited to:
• Visual appeal
• Ease of navigation
• Overall user experience
• Your prototype's ability to extract relevant information accurately from resumes
• Algorithm development for candidate selection and accuracy (20 points)
• Ability of the algorithm used to provide accurate and meaningful results that align with the project's objectives
• Effectiveness of the algorithm used for candidate selection, ensuring it can accurately rank candidates based on their qualifications and suitability for specific job roles
• Question generation and alignment to Candidate (20 points)
• Prototype's ability to generate relevant and appropriate interview questions based on candidate profiles or job requirements
• How well the generated questions align with each candidate's qualifications and how effectively they assess their suitability for the role.
• Screening Interview and Evaluation (20 points)
• Screening interview process, including its structure, effectiveness, and ability to assess candidate skills and fit
• Captures and evaluates candidate responses during the interview process
• Speed (10 points)
• Speed and responsiveness of the project, ensuring it can handle a reasonable number of candidates or resumes efficiently
• How quickly the prototype performs tasks and provides results without compromising accuracy
• Value adds (20 points)
• Identify additional features, functionalities, or innovative aspects that the prototype offers beyond the basic requirements
• How these value-adds contribute to enhancing the HR process and overall project goals