AI MOCK INTERVIEW

PROJECT TEAM MEMBERS:

21ME1A05G4 Mr. K. Yashwanth Balakumar

21ME1A05J7 Ms. G. Hema Madhuri
21ME1A05G7 Mr. M. Veera Babu
22ME5A0514 Mr. K. Lohit
Mentor: J. Neeraja
Assistant Professor
Department of Computer Science and Engineering
05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 1
CONTENTS:
Introduction & Background
Problem Statement & Objectives
Literature Survey
 Existing / Traditional system
Methodology / Proposed System
Hardware & Software Requirements
Design & Implementation
Results & Observations
Advantages & Applications
Conclusion
References
05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 2
 Introduction & Background
Job interviews are a critical component of the recruitment process, allowing employers to evaluate candidates'
technical skills, problem-solving abilities, communication style, and cultural fit. However, many applicants—
especially fresh graduates, career switchers, and individuals from underrepresented backgrounds—face challenges
in preparing for interviews due to a lack of access to mentorship, mock sessions, or constructive feedback.

In recent years, Artificial Intelligence (AI) has seen significant advancements across a wide range of applications,
including education, healthcare, finance, and recruitment. One notable and emerging use case is in the field
of interview preparation. Traditional methods of preparing for job interviews—such as reading guidebooks,
watching videos, or practicing with friends—often lack personalization and real-time feedback. Additionally, many
candidates, especially fresh graduates or individuals switching careers, may not have easy access to experienced
mentors or mock interviewers.

05/28/2025 PROJECT BATCH : [CSE], AY: 2024-25 3

 Introduction & Background (Contd…)
This project is designed to serve as a virtual interview coach, helping users practice common and domain-specific
interview questions through interactive sessions. The system is capable of understanding user responses, analyzing
content and delivery, and offering personalized feedback on performance. By integrating AI technologies, the project
not only enhances interview preparedness but also boosts users' confidence, communication skills, and ability to think
under pressure.

Key words:
• Answer Evaluation
• Natural Language Processing (NLP)
• Technical Interview Preparation
• Full-Stack Development
• User Performance Insights (Expression analysis)
• Real-Time Feedback
• AI Mock Interview Platform
05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 4
Problem Statement

Preparing for job interviews is a major challenge for many candidates, particularly those without access to mentors,
professional coaching, or mock interview opportunities. Traditional preparation methods—such as reading interview
guides, watching tutorials, or practicing alone—often lack personalization, real-time interaction, and actionable feedback.
As a result, many candidates enter interviews feeling unprepared, anxious, and unsure of how to improve.

There is a growing need for a smart, accessible, and interactive solution that can help individuals practice and improve
their interview skills in a realistic, feedback-driven environment.

Additionally, human-led mock interviews can be costly, time-consuming, and difficult to scale. There is a clear need for an
intelligent, automated system that can provide users with a realistic interview experience, identify areas of improvement,
and offer personalized feedback to enhance their readiness.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 5

KEY OBJECTIVES:
1. Create a platform that simulates real interview questions.
2. Use AI to understand and evaluate user responses
3. Provide instant feedback to help users improve their answers
4. Score responses based on accuracy, relevance, and confidence.
5. Track user progress over time to show improvement areas.
6. Make the platform easy to use and accessible online.
7. Support both technical and behavioral interview preparation.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 6

Literature Survey

Relevant references

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 7

Literature Survey

Relevant references

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 8

Existing / Traditional System

The Existing System refers to the current solutions available in the market for mock interviews, particularly those that
are AI-based or use video and webcam features. We assess what features these systems already offer, their limitations,
and how they can be improved.

• Overview of Current Mock Interview Systems:

• Many existing platforms provide mock interviews for job candidates, but they primarily focus on verbal
responses and question banks.

• Examples include platforms like Interviewing.io, Pramp, and HireVue. These platforms may use video
recordings or live interviews, but often don’t offer the integration of non-verbal feedback (facial expressions,
gestures).

• These platforms may use video interviews but typically do not analyze or provide feedback on body
language or facial expressions, both of which are crucial in real interviews.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 9

Existing / Traditional System
• Limitations of Existing Systems:

• Limited non-verbal feedback: Most systems only assess the verbal response but fail to analyze non-verbal cues (gestures,
facial expressions, eye contact, etc.).

• Generic questions: Current platforms offer generic mock interviews but do not personalize the experience by customizing
questions based on company and role.

• Lack of Real-Time Analysis: Existing platforms typically do not analyze facial expressions or gestures during the interview
in real-time or provide instant feedback.

• No performance tracking: Many platforms don’t track a candidate's performance over time or suggest specific areas for
improvement (e.g., eye contact, tone of voice, gestures).

• What’s missing?

• Real-time feedback: Existing systems don’t provide instant feedback on body language or emotional cues during the interview.

• Body language and facial expression analysis: These are critical aspects of human interaction that are not analyzed by most
mock interview platforms.

• Role and company-specific interviews: Few platforms customize questions based on the exact role or company the candidate
is applying to, reducing the mock interview’s effectiveness in simulating real interviews.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 10

Methodology / Proposed System:
• The Proposed System is the AI Mock Interview system you are developing. This system aims to overcome the
limitations of the existing systems by offering AI-based personalized mock interviews that also evaluate non-
verbal cues using facial expression analysis and gesture recognition via webcam.

• Key Features and Components of the Proposed System:

• Personalized Interviews Based on Role and Company:

• Tailored Question Sets: The AI system will generate interview questions specifically related to the company
and role the user selects. This customization increases the authenticity and relevance of the mock interview,
providing a more accurate practice session.

• Adaptive Difficulty: The system can adjust the difficulty of questions based on the user’s previous answers,
making the interview progressively more challenging as the user improves.

• Real-Time Feedback on Verbal and Non-Verbal Performance:

• Verbal Analysis: The system uses Natural Language Processing (NLP) to evaluate the user’s responses, assessing
clarity, tone, confidence, and relevance of the answer.
05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 11
Methodology / Proposed System (Contd…)
• Facial Expression Analysis: The system uses computer vision technologies (OpenCV, dlib) to detect and analyze
facial expressions like smiling, frowning, eye contact, nodding, and other expressions that indicate engagement,
confidence, and stress.

• Gesture Recognition: The webcam will also capture gestures such as hand movements, posture, and overall body
language. The system uses machine learning to recognize positive and negative gestures that could impact the
impression made during an interview.
Web Interface with Camera Access:
• User-Friendly Interface: The system will run on a web interface, allowing easy access via any browser. Users will be
able to interact with the system by simply logging in and using their webcam.
• Camera Integration: The system utilizes the webcam to record and analyze facial expressions and gestures during
the interview.
Backend with Python:
• The backend is powered by Python using frameworks such as Flask or Django. Python is ideal because of its
extensive libraries for machine learning (e.g., OpenCV) and its compatibility with NLP and computer vision models.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 12

Hardware Requirements

•Processor: Intel Core i5 or above / AMD Ryzen 5 or above

•RAM: Minimum 8 GB (Recommended: 16 GB)

•Storage: Minimum 256 GB SSD

•GPU (Optional): NVIDIA GPU (e.g., GTX 1650 or higher) for faster AI/ML processing

•Webcam & Microphone: Required for video and voice interaction

•Internet Connection: Stable connection for accessing APIs and online services

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 13

Software Requirements
Programming & Development

•Language: Python (main language for AI and backend logic)

•IDE/Editor: VS Code, PyCharm, or Jupyter Notebook
•Version Control: Git, GitHub
Frontend Technologies: HTML, CSS, JavaScript, React.js

Backend & APIs

•Frameworks: Flask or Django (Python-based)

Computer Vision
•Library: cv2 (OpenCV)
•Capture and process webcam video
•Detect face presence during mock interview
•(Optional) Analyze facial expressions and eye contact

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 14

Design & Implementation
 Circuit diagrams / Schematics / Algorithms

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 15

Design & Implementation (Contd…)

 Prototype development

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 16

Results & Observations

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 17

Results & Observations (Contd…)

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 18

Results & Observations (Contd…)

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 19

Results & Observations (Contd…)

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 20

Advantages
• Personalized Interview Practice: Offers tailored mock interviews based on the user’s background, skill level, and job
role.
• Real-Time Feedback: Provides instant, constructive feedback to help users identify strengths and improve weak areas.
• Increased Accessibility: Accessible anytime, anywhere—ideal for users without access to in-person coaching or
mentorship.
• Cost-Effective: Reduces the need for expensive coaching sessions or professional interview training.
• Skill Development: Enhances both technical and soft skills such as communication, confidence, and problem-solving.
• Inclusive Support: Especially helpful for fresh graduates, career switchers, and underrepresented candidates who may lack
traditional support systems.
• Consistent Practice: Encourages regular, repeatable practice which is key to mastering interview performance

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 21

Applications
• Job Seekers & Fresh Graduates: Helps individuals prepare for entry-level roles by simulating real interview
scenarios and providing feedback on performance.
• Career Switchers: Assists professionals transitioning into new industries by tailoring questions and guidance to
their target roles.
• Educational Institutions: Can be integrated into career services at universities and colleges to support students
with mock interviews and skill development.
• Recruitment Agencies: Used by agencies to pre-screen candidates or help them improve before presenting them
to employers.
• Corporate Training Programs: Companies can use the tool to train new hires or upskill employees for internal
role changes and promotions.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 22

Conclusion
KEY FINDINGS:

• Job interviews are essential for assessing candidates’ skills, communication, and cultural fit.

• Many candidates—especially fresh graduates, career switchers, and underrepresented groups—

struggle with interview prep due to limited access to mentorship, mock interviews, and feedback.

• Traditional preparation methods (books, videos, peer practice) often

lack personalization and real-time evaluation.

• AI-powered tools are emerging as a promising solution, providing customized interview

simulations, immediate feedback, and greater accessibility for diverse users.

AI has the potential to revolutionize interview preparation by making it more accessible, efficient, and
tailored to individual needs. By bridging gaps in mentorship and resources, AI can help level the playing
field for job seekers from all backgrounds, fostering a more inclusive hiring process and improving
candidates' chances of success.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 23

References
1. S. Kim, S. Y. Park and H. Ko, "Artificial intelligence-based mock interview system using natural language
processing," 2020 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 2020, pp. 1-2.
doi: 10.1109/ICCE46568.2020.9042973
2. R. F. Mahmood, S. M. Anwar and M. Majid, "Real-time facial expression recognition using deep learning for monitoring
behavior in online interviews," IEEE Access, vol. 8, pp. 136740–136752, 2020.
doi: 10.1109/ACCESS.2020.3011174
3. G. A. Elia, V. Catania, M. Fiore, and F. Cutugno, "A Virtual Interviewer Based on NLP for Student Soft Skills
Assessment," 2022 IEEE Global Engineering Education Conference (EDUCON), 2022, pp. 1153-1157.
doi: 10.1109/EDUCON52537.2022.9766743
4. J. Park, D. Yoo, Y. Lee and S. Cho, "Development of Interview Coaching Chatbot System Using Deep Learning and
NLP," 2019 IEEE International Conference on Big Data and Smart Computing (BigComp), 2019, pp. 1-4.
doi: 10.1109/BIGCOMP.2019.8679222
5. D. Kumar, A. Saha and A. Ghosh, "Virtual Personal Assistant for Interview Training Using NLP and Speech
Recognition," 2021 6th International Conference on Communication and Electronics Systems (ICCES), 2021, pp. 1548-
1553.
doi: 10.1109/ICCES51350.2021.9489155
6. S. K. Singh and P. Singh, "AI Based Interview Preparation System for Students: A Review," 2021 International Conference
on Computing, Communication, and Intelligent Systems (ICCCIS), 2021, pp. 899-902.

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 24

05/28/2025 PROJECT BATCH #: [ECE/A2], AY: 2024-25 25