Industrial Engineering Journal

ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

AI BASED RESUME ANALYZER AND CAREER GUIDANCE SYSTEM

Mrs. Alka Kumbhar, Assistant Professor, Dept. Of Computer Engineering, Genba Sopanrao Moze
College of Engineering, Pune, India
Hrishikesh Alabnur, Student, Department of Computer Engineering, Genba Sopanrao Moze
College of Engineering, Pune, India
Ankit Kumar, Student, Department of Computer Engineering, Genba Sopanrao Moze College of
Engineering, Pune, India
Shantanu Bhandakkar, Student, Department of Computer Engineering, Genba Sopanrao Moze
College of Engineering, Pune, India
Hetavi Manani, Student, Department of Computer Engineering, Genba Sopanrao Moze College of
Engineering, Pune, India

ABSTRACT:
This project focuses on developing an AI and ML-driven system designed to enhance both recruitment
processes and career development. For HR professionals, the system automates the analysis of
resumes, extracting key skills and identifying skill gaps between the candidate's experience and the
requirements of the job role. By using machine learning models such as Random Forest, the system
classifies resumes into relevant job categories and offers feedback on the proficiency of specific skills
through aptitude testing, enabling HR to streamline recruitment and identify suitable candidates more
effectively.
For students, the system offers a personalized approach to career development by predicting suitable
job categories based on their uploaded resumes and recommending relevant courses to bridge any skill
gaps. By combining advanced techniques in natural language processing (NLP) and machine learning,
this project aims to enhance the career prospects of students while also optimizing the recruitment
process for HR professionals. The system’s capabilities offer significant improvements in both hiring
efficiency and skill-based career growth.
Keywords: Career path, Machine Learning, Artificial Intelligence, Natural Language Processing,
Resume Analyzer, Large Language Model, Skills

INTRODUCTION:
This rapidly transforming job market in the face of rapid technological changes and the dynamic
demands of the industries, presents both employers and employees with the daunting task of matching
up the gaps. Current methods of recruitment through resumes and resume screening by the recruiter or
human resources staff is long drawn, vulnerable to biases, and largely inefficient. Therefore, this
creates unaccounted-for talent and a wrong hire in many cases.
AI and ML-driven solutions can, therefore, help in automating resume analysis and identifying skill
gaps, thereby allowing for personalized career guidance. The research aims at developing an intelligent
system that makes recruitment easier and enhances decision-making while empowering the job seeker
in aligning the skills with the industry demands. This approach of bridging the skills gap is likely to
make the workforce efficient, reduce the cost of hiring, and enhance lifelong learning toward a more
adaptive and competitive job market.

LITERATURE SURVEY:
There has been an increased focus on the application of Artificial Intelligence (AI) and Machine
Learning (ML) in career guidance and job recommendation systems in recent times. Different
approaches to improving employability through advanced algorithms for career prediction, resume
analysis, and skill gap identification have been studied in different studies. Though promising results

UGC CARE Group-1 48

 Industrial Engineering Journal
ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

are observed with these systems, issues regarding data quality, model accuracy, and scalability also
come up.
Sneha H. S. et al. proposed an AI-driven career guidance system using Naïve Bayes classifiers and
NLP-powered chatbots to provide career recommendations based on academic performance and skill
assessments. The system interacts with students to assess their skills and interests, offering
personalized career suggestions. Although it effectively enhances career decision-making, it fails to
process unstructured resumes and ensures accuracy in its predictions. Because career choices depend
on a lot of factors, including industry demand and personal aspirations, the system would need further
optimization in providing a more holistic direction.
Prashanth V. J. et al. presented a resume analysis tool that employs CNNs and word2vec to predict the
appropriate job role based on resume information and offer recommendations to upgrade related skills.
The system extracts major features of a resume, analyses skill gaps, and recommends improvements,
bringing candidates' profiles in line with industry needs. Despite being proficient in detecting missing
skills and targeted recommendations, it fails with multilingual resumes and the complexities inherent
to unstructured data formats, limiting its utility for diverse groups of users. In addition, the model will
tend to favour well-structured resumes over less conventional formats in its recommendations, and
fairness in recommendations is a concern.
Hude T. et al. performed an extensive review of AI-based career counselling, which reviewed systems
that utilized Support Vector Machines (SVMs) for personalized career recommendations. These
models improve job matching by analysing user skills and market trends; however, their effectiveness
is largely dependent on the quality and completeness of the input data. This review also brings into
focus real-time job market trends, aptitude assessments, and interactive career quizzes that help to
enhance the ability of the system to give relevant career suggestions. However, some of the drawbacks
include concerns regarding data privacy, algorithmic bias, and model transparency. Therefore, AI-
driven career counselling should ensure that there are no biased recommendations and ensure the
protection of user data for credibility and trust.
Overall, the studies highlight an increasing role for AI and ML in career counselling and job matching
but also present significant areas of improvement. Success in these systems depends on the diversity
of the data, model robustness, and adaptability to changing job market trends. Future research should
target the improvement of the accuracy of AI models by incorporating real-time labour market insights
and developing adaptive learning mechanisms for more precise, fair, and inclusive career
recommendations. Further integration of psychometric evaluations, soft skills assessments, and
industry-specific career pathways would further refine the guidance provided and ensure a holistic and
personalized approach to career development.

PROPOSED SYSTEM:
The design of the proposed system shall focus on two major target groups: HR professionals and
students. It shall focus on distinctly different demands yet interrelated needs of these two groups in the
hiring and career development process.
For HR professionals, the system dramatically augments and streamlines the recruitment workflow
using such advanced technologies as Machine Learning (ML), Natural Language Processing (NLP),
and AI-driven recommendations. One of its key features is the automated extraction of essential skills
from resumes, which reduces the manual effort required to screen candidates effectively. The system
can intelligently predict the most suitable job categories for applicants by analysing the extracted skills,
thus ensuring better alignment between candidates and job roles. It also identifies skill gaps by
comparing the candidate's qualifications with job requirements, thus helping recruiters make more
informed hiring decisions. These include aptitude assessments within the system. The system evaluates
the proficiency of a candidate in specific subjects and will provide insightful feedback that will help

UGC CARE Group-1 49

 Industrial Engineering Journal
ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

improve the selection process. This further limits the role of manual screening, minimizes biases
associated with the process, and leads to an efficient, fair, and data-driven hiring approach.
The system offers quality career guidance for students and job seekers by going through their resume
and predicting a probable job category based on what they are possessing at the present moment. That
way, a person gets more clarity about their career path suited to them. The system automatically
identifies the areas of skill deficiencies and gives proper recommendations in regard to courses or
certifications or trainings that one can undertake for filling those skills. This enables students to upskill
effectively for improving their prospects of employability. With AI-driven career guidance
incorporated, student access is provided with personalized insight, thereby having a strategic and
efficient approach toward job search.

AIMS AND OBJECTIVES:

AIM:
This project is intended to help HR professionals screen, assess, and hire the right candidates efficiently
using leading-edge Artificial Intelligence (AI) and Machine Learning (ML) technologies. The system
automates primary resume analysis, skill evaluation, and job role identification to decrease manual
effort, improve decision-making, and make the recruitment process more accurate and unbiased. The
project further aims to offer students career guidance and personalized suggestions to maximize their
employability.

OBJECTIVES:
Simplify the Recruitment Process:
The system is designed to streamline and optimize the recruitment process by automating candidate
screening and resume evaluation. Through resume analysis for skill gaps and job role fit, HR
professionals can make faster, data-driven hiring decisions. This minimizes the time spent on manual
resume screening and ensures that the best candidates are identified in an efficient manner, thus
enhancing overall recruitment productivity.
Improve Resume Assessment:
Using Natural Language Processing (NLP), the system identifies relevant skills, qualifications, and
experiences from resumes. It uses Machine Learning (ML) algorithms to categorize resumes into
suitable job categories so that each candidate is matched with the most appropriate job role. This
feature enhances the accuracy of resume evaluation and the hiring process by matching candidates
with job opportunities that best suit their skill set.
Offer feedback and learning paths:
The system provides comprehensive, AI-based feedback to candidates on their strengths, weaknesses,
and areas of improvement. It detects missing skills that are critical for target job roles and suggests
individualized learning pathways by proposing suitable courses, certifications, or training programs.
This method allows job seekers to close skill gaps efficiently, making them more competitive in the
labour market.
Helping Career Development in Students:
For job applicants and students, the system acts as a career guidance system by scanning their resumes
and identifying their current career category. It offers intelligent recommendations on skills they need
to learn in order to enhance their employability and move up in their desired career paths. Through its
AI-based suggestions for upskilling and reskilling, the system ensures that students are equipped to
compete in a fast-changing job market.

SCOPE OF PROJECT:

UGC CARE Group-1 50

 Industrial Engineering Journal
ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

It takes advanced AI and Machine Learning capabilities to elevate not only the processes of recruiting
people but also developing career-related solutions. In its resume analysis enhancement, automated
resume review with increased skill gaps recognition, categorization of jobs by type, resume scoring,
resume filtering based on key competencies, it contributes significantly in providing insights about
people.
For HR Professionals: It saves the traditional, time-consuming resume screening process and
intelligently filters candidates on various parameters such as specific skills, experiences, qualifications,
and job role relevance. It provides insights to the HR professional using AI-driven inputs for data-
driven hiring decisions and saves manual effort, thereby accelerating the recruitment cycle.
For Job Seekers: It provides highly personalized career support by analysing resume s, identifying
what may be missing or improving, and publishing relevant career recommendations. The portal offers
career advice from the potential job roles, job market trends, and skill-building courses for bridging
gaps in skills. This personalized approach helps candidates understand their strength and where they
need improvement while providing access to practical resources that will be a better step toward
increasing their employability.
Currently, the system supports resumes in English language, but in the future updates, it will be
multilingual to reach a global audience. Moreover, it is planned to introduce more advanced AI-driven
assessments that will evaluate not only technical skills but also aptitude and soft skills of candidates.
This should help the project enhance job matching, increase efficiency in hiring, and empower job
seekers with actionable, data-driven insights that help them thrive in a competitive job market. It is an
all-around seamless AI-powered ecosystem supporting recruiters and candidates alike in the pursuit of
professional goals.

METHODOLOGY
Skill Extraction with NLP and LLM:
Skill extraction is achieved through the Natural Language Toolkit (NLTK) for Natural
Language Processing (NLP). An extracted skill is converted into structured JSON form by a Large
Language Model (LLM) to categorize and analyse efficiently. Automation of the process lessens
manual effort and enhances accuracy in skill detection.
Extraction Process:
Preprocessing: Stop word removal, punctuation stripping, and tokenization to normalize and clean the
text.
Skill Identification: By employing Named Entity Recognition (NER) and Part-of-Speech (POS)
tagging to recognize and extract relevant skills.
LLM Refinement: Forwarding extracted skills through an LLM to normalize, disambiguate, and
format as structured JSON for further analysis.
Machine Learning Model for Skill Assessment:
Skill proficiency is quantified with a Random Forest model, well-known for its accuracy and ability
to capture non-linear relationships. The model is trained to forecast proficiency based on a candidate's
resume attributes and other input features. Hyperparameter tuning is employed to enhance performance
and enhance generalizability.
Training Process:
Data Collection: A labelled dataset of skill levels, previous performance measures, and job success
rates is constructed.
Feature Engineering: Extracting relevant features such as years of experience, successful project count,
relevant certificates, and educational qualifications.
Model Training: A Random Forest model is trained and tuned using Grid Search and
Bayesian Optimization to boost prediction accuracy.

UGC CARE Group-1 51

 Industrial Engineering Journal
ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

Evaluation Metrics: Performance is evaluated using accuracy, precision, recall, F1-score, and cross-
validation strategies to avoid overfitting.
Aptitude Question Generation using LLM:
An LLM creates dynamic aptitude-based multiple-choice questions (MCQs) based on the extracted
skills to further evaluate candidate proficiency.
Generation Process:
Skill-Based Prompting: The LLM consumes extracted skills as input and produces aptitude questions
pertinent to the skills.
Difficulty Calibration: The difficulty level of questions generated is dynamically calibrated according
to the responses of earlier candidates.
Response Analysis: The system assesses responses against pre-defined metrics of correctness and
improvement or deterioration patterns.

SKILL LEVEL MEASUREMENT BASED ON OUTPUT PERFORMANCE:

Candidate ability is assessed through an ML-based scoring mechanism that takes into account various
performance metrics.
Evaluation Criteria:
Response Accuracy: Measures the percentage of correct responses to questions.
Response Time: Analyses the time taken to respond to each question, providing insights into ability
and confidence.
Complexity Handling: Checks whether the candidate responded to more complex questions correctly.
The output is mapped to pre-defined ability levels (Beginner, Intermediate, Advanced) for an objective
skill evaluation.

ATS SCORE CALCULATION:

The ATS score is calculated to determine how well a resume matches a job description, enhancing
recruitment efficiency.
ATS Scoring Factors:
Skill Relevance: Measures the similarity between extracted skills and job requirements.
Keyword Optimization: Checks the presence of industry-specific keywords that improve resume
visibility.
Resume Structure & Formatting: Checks for clarity, readability, and compliance with industry
standards.
Match Percentage: Calculates the percentage of required qualifications matched by the candidate.
A weighted scoring algorithm allocates points to each factor, resulting in an overall ATS score that
recruiters can utilize to shortlist candidates efficiently.

CONCLUSION:
In summary, this project is able to successfully leverage the power of Artificial Intelligence and
Machine Learning to optimize both skill development and recruitment efficiency. By utilizing
sophisticated AI-based methods, it automates significant parts of resume analysis, career guidance,
and job role prediction, thus decreasing the manual effort involved in conventional hiring procedures.
The use of the Random Forest algorithm is a key factor in predicting job categories accurately from
derived resume data. By examining the skills declared on a candidate's resume and matching them
with relevant industry job requirements, the system delivers accurate information on the most
appropriate career paths. It also determines the current skill gaps, enabling both job seekers and HR
professionals to make informed decisions about hiring and career progression.

UGC CARE Group-1 52

 Industrial Engineering Journal
ISSN: 0970-2555
Volume : 54, Issue 2, No.2, February : 2025
[

For HR practitioners, this process improves the hiring process by supporting data-driven decision-
making. Rather than using purely subjective resume screening, recruiters are provided with AI-based
feedback that identifies a candidate's strengths and weaknesses. This reduces the influence of human
bias, facilitates a more objective assessment, and accelerates the hiring process. Additionally,
automated aptitude tests further improve candidate assessment by allowing recruiters to view a
candidate's level of expertise in areas of key skills using a quantitative score.
From the student's point of view, the project presents a proactive career development strategy. Through
resume analysis and job category prediction, the system gives students personalized career advice,
enabling them to know where they are in the job market. More significantly, the system takes it a notch
higher by providing AI-based course suggestions that match the forecasted job positions. This
capability allows students to fill their skill gaps effectively, becoming more competitive and having
better chances of landing the desired job opportunities.
In proving the capability of AI to streamline and optimize talent acquisition and professional
development, the project showcases technology's catalytic effect in contemporary hiring and learning.
Beyond simplifying candidate sourcing, this system also enhances ongoing learning to keep students
and professionals up-to-date in an ever-changing workforce. In effect, this system makes the
recruitment and hiring process more efficient, better-informed, and more balanced for both employers
and workers, solidifying the position of AI as an effective driver of workforce development.

REFERENCES:
[1] Rajput, A., Dubey, A., Thakur, R., Singh, D., & Singh, U. P. (2024). Career Craft AI: A personalized
resume analysis and job recommendations system. IEEE Xplore, 1–6.
https://doi.org/10.1109/istems60181.2024.10560126
[2] Soni, N., Nishant, N., Singh, M., Ansari, S., Siddiqui, A. T., & Ansar, S. A. (2023). Leveraging machine
learning for career prediction and resume analysis in career assist. 2018 5th IEEE Uttar Pradesh Section
International Conference on Electrical, Electronics and Computer Engineering (UPCON), 1009–1014.
https://doi.org/10.1109/upcon59197.2023.10434306
[3] Mankawade, A., Pungliya, V., Bhonsle, R., Pate, S., Purohit, A., & Raut, A. (2023). Resume analysis and
job recommendation. 2022 IEEE 7th International Conference for Convergence in Technology (I2CT), 1–5.
https://doi.org/10.1109/i2ct57861.2023.10126171
[4] Katkar, S. V., Popli, R., Bansod, A. S., Laddha, V. N., Sukode, A. S., & Newale, S. R. (2024). AI/ML
BASED CAREER GUIDANCE TOOL. In Industrial Engineering Journal (Vols. 53–53, Issue 4, pp. 100–
101).
[5] Raut, P. G., & Wagh, R. D. (2024). Resume Analyzer and Recommender System Using Python.
International Journal of Research Publication and Reviews, 5(6), 6245–6253. https://www.ijrpr.com
[6] Hude, T., Bagal, A., Kazi, A., Gaikwad, A., & Sarvade, H. (2024). Review of AI based career Counselling.
International Journal of Advanced Research in Science Communication and Technology, 385–388.
https://doi.org/10.48175/ijarsct-17561
[7] Gokarn, S., Taware, S., & Vartak, R. (2024). Smart Career Guidance System Using Machine Learning.
International Journal of Science and Research (IJSR), 13(6), 1140–1144.
https://dx.doi.org/10.21275/SR24612203820
[8] Gilbile, S. J., Sutar, A. U., Pandit, V. S., Desai, S. R. (2023). ONLINE CAREER COUNSELLOR
SYSTEM BASED ON ARTIFICIAL INTELLIGENCE. In Journal of Emerging Technologies and
Innovative Research (Vol. 10, Issue 5). https://www.jetir.org
[9] Sayyed, F., Sanghani, R., Vora, A., Lemos, N., & Xavier Institute of Engineering. (2020). AI based Career
Guidance. In International Research Journal of Engineering and Technology (IRJET) (Vol. 07, Issue 05, p.
2505).
[10] Ghuge, M., Kamble, T., Mandrawliya, A., Kumari, A., & Raikwar, V. (2023). Envisioning
Tomorrow: AI Powered Career Counselling. IEEE Xplore, 377–383.
https://doi.org/10.1109/icimia60377.2023.10426016

UGC CARE Group-1 53