Personalized Career Path Recommendation Model for Information Technology Students

Abstract

The ever-growing complexities of today’s career markets leave most students confused while choosing a career. Conventional counselling methods usually depend on pre-conceived notions and ignore the actual state of affairs, both regarding the market and the student’s overall profile. In this paper, we present an AI-powered website that uses machine learning algorithms to offer students data-backed advice about their careers. Using various parameters such as academic record, technical expertise, personal interest and aptitude, the system uses K-Means Clustering and Random Forest algorithm to offer predictions for the right career choices. Moreover, the system offers annual career guidance in light of the current market situation. An experiment yielded an accuracy rate of 91%.

Introduction

The text describes the implementation and performance of a Personalized Career Path Recommendation System that transforms traditional career counseling into a fully digital, data-driven process. The system integrates machine learning, real-time updates, and interactive dashboards to provide accurate, reliable, and personalized career guidance for students, while also benefiting counselors and administrators.

The model is designed to be scalable, adaptable, and responsive, incorporating dynamic data such as industry trends, job market demands, and user feedback. Its modular architecture allows easy expansion with features like analytics, learning pathways, and job matching, ensuring continuous improvement and relevance.

The process follows several key steps:

• User profiling collects academic, skill, and interest data for a holistic assessment.
• Resume analysis using NLP extracts skills and experience automatically.
• AI-based prediction uses K-Means clustering and Random Forest to identify suitable career domains and roles.
• Skill gap analysis evaluates readiness and highlights missing skills.
• Career roadmap generation provides a structured plan with skills, courses, projects, and timelines.
• Real-time dashboards and notifications keep users updated with progress and opportunities.
• Centralized data management ensures tracking, accountability, and future analysis.
• Cloud deployment supports scalability and high user demand.

Results show that the proposed system achieves high accuracy (around 91%), outperforming traditional rule-based (68%) and basic machine learning (79%) approaches. It also improves processing efficiency and effectively reduces skill gaps.

Overall, the system creates a comprehensive ecosystem that links education with career opportunities, offering practical, personalized, and continuously updated career guidance.

Conclusion

In the proposed AI-Based Career Path Recommendation System, the system efficiently suggests career paths based on academic results, technical skills, preferences, aptitude test responses, and resume review. It is important to note that not only does this system help determine the right career domains by applying clustering and classification techniques, but it also provides structured career paths that will enable the student to realize their career dreams. By combining skill-gap assessment and market fit, the recommendations provided are realistic and relevant to the industry, hence fulfilling the true objective of career counseling. The K-means clustering algorithm and random forest classification algorithm used in the recommended career path system complement each other very well and offer supplementary functionalities like readiness scores, personalized dashboards, and career path timelines. Therefore, the AI-based career path recommendation system provides a reliable and intelligent solution for students, which eliminates the need for generic advice and enables them to make informed career choices. Future improvements on the AI Based Career Path Recommendation System include the integration of APIs for real-time updates on new technology and trends in job markets. Other features may involve personality assessment, adaptive feedback loops, and deep learning algorithms. The system may also be enhanced through mentoring services, mobile applications, and scalable cloud hosting services to ensure user convenience

References

[1] An AI-driven career guidance model was put forth by Hossain M. Z. et al. (2022), which takes into consideration personality characteristics and helps students choose careers best suited to their abilities and preferences.. [2] \"Biswal A.K., et al.\" introduced a smart education recommendation system aimed at improving students’ learning results by providing customized recommendations. In order to accomplish the goal, learner information is utilized in combination with students’ academic records for the purpose of recommending learning material as well as choosing career paths. [3] Zhang Y. and Zhu S. (2021) studied the use of edge intelligence to perform student analytics. Their paper discusses the use of edge intelligence in order to analyze behaviors and performances of students. [4] Al-Mansoori A. et al. (2021) - Machine Learning in Educational Decision MakingSystem based on machine learning algorithms to facilitate educational decisions for students developed by Al-Mansoori A. et al. [5] Patel R. and Shah N. (2022) – Personalized Recommendation SystemsPatel R. and Shah N. presented a personalized recommendation framework that adapts suggestions based on user profiles and historical data. [6] Chen L., et al. (2020) - Data Mining for Student Profiling In their research, Chen L., et al., considered the potential application of data mining approaches to develop detailed student profiles based on academic information and behavior. They utilized clustering and classification approaches to classify students having common attributes. It was found that student profiling approaches based on data mining techniques could provide substantial assistance to personalized guidance systems. [7] Singh A. et al. (2021) – Skill Recommendation in Education Singh A. et al. proposed a skill recommendation system that identifies skill gaps in students by analyzing their academic background and learning history. [8] Li X. and Wang Y. (2022) - AI-Powered Career Guidance Systems The research by Li X. and Wang Y. presents an innovative AI-powered career guidance system that integrates both personality testing and future predictions for suggesting appropriate career options. The system proves to be more accurate than conventional career counseling techniques. Nevertheless, the research highlights only career forecasting, failing to offer relevant learning paths or employment integration. [9] Rahman M. et al. (2021) – Educational Recommendation Systems Rahman M. et al. investigated recommendation systems in educational environments that utilize collaborative filtering and content-based techniques. [10] Zhao H. et al. (2020) – Job Recommendation Systems Zhao H. et al. proposed a job recommendation system that matches candidate profiles with job descriptions using text mining and machine learning.

Copyright

Copyright © 2026 C Tamilarasi, Lokesh Bharathi N, Hari Prasath P. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.