CareerAstra: An AI-Powered Hybrid Recommendation System for Career Guidance of Indian Students

DOI

10.2991/978-94-6239-693-7_104How to use a DOI?

Keywords

Career guidance; artificial intelligence; hybrid recommendation system; large language models; machine learning; cognitive profiling; subject–career alignment; AI in education; entrance exam prediction; scholarship recommendation

Abstract

Many students in India have difficulty with career. Decisions out of lack of structured and affordable guidance. In particular in rural and semi-urban areas. Most existing digital. Career guidance tools are not to the Indian. Education which also does not take into account subject eligibility, entry. Issues of exam performance and financial constraints. To that end, this. Paper reports on CareerAstra which is a hybrid AI based career guidance solution. Platform which is for Indian students. The system. Integrates machine learning models and large language models. Cognitive assessment, and rule-based subject–career alignment. To develop tailored and realistic career suggestions. At CareerAstra we also present to you related fields of work that fit you best trance examinations, scholarship opportunities, and customized study roadmaps. A weighted system we have which puts 70% into machine learning predictions which are structured and 30% into contextual reasoning from large language models which we use for the final recommendation score. We have put together a platform which uses React for the front end, Flask for the backend, and a PostgreSQL database, also we have adaptive question generation which we support via Google Gemini. We did a pilot study with 50 users which reported very strong subject career match, high relevance of recommendations and very positive user feedback which we also saw an average recommendation generation time of under 10 s. What we found is that by putting together data driven models with contextual reasoning we greatly improved the access and quality of career guidance for Indian students.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - T. V. Sree Vastha
AU  - R. Raja Subramanian
AU  - P. Thisyanth
AU  - T. Venu Babu
AU  - P. Srikanth
PY  - 2026
DA  - 2026/06/16
TI  - CareerAstra: An AI-Powered Hybrid Recommendation System for Career Guidance of Indian Students
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 1078
EP  - 1089
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_104
DO  - 10.2991/978-94-6239-693-7_104
ID  - Vastha2026
ER  -