Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{194380,
        author = {Daakshayani NS and Divya Prabha G and Kavitha R and Vijayalakshmi},
        title = {EuroPath AI - leveraging Artificial Intelligence to Streamline European Higher Education Access for International Students},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8276-8282},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194380},
        abstract = {Europath AI is an intelligent web-based decision support platform designed to guide students through the complex and often overwhelming process of selecting the right European university and academic programme. With thousands of universities and hundreds of degree programmes spread across Europe, prospective students frequently struggle to identify options that align with their academic qualifications, financial constraints, career ambitions, language proficiency, and geographic preferences. Europath AI addresses this challenge by combining large language model (LLM) reasoning with a multi-criteria matching algorithm to deliver personalised, ranked, and explainable university recommendations. Built using a modern React frontend, FastAPI backend, and a PostgreSQL/SQLAlchemy data layer, the platform enables students to complete a structured profile, receive AI-generated recommendations in seconds, compare programmes side- by-side, and understand exactly why each university was suggested through natural language rationale. Unlike conventional university search engines, Europath AI calculates a composite fit score based on five weighted criteria: academic eligibility, field alignment, financial feasibility, language compatibility, and location preference. A continuous feedback loop collects user ratings and acceptance decisions to iteratively retrain the matching weights, improving recommendation quality over time.},
        keywords = {},
        month = {March},
        }