Explainable AI-based Career & Institution Recommendation System for Higher Secondary Students

The transition from higher secondary education to specialized academic or professional paths is a critical period for students, particularly in India's diverse educational context with multiple boards (CBSE, ICSE, State Boards) and over 5,000 undergraduate programs. Existing digital career guidance systems have three major limitations: lack of transparency in how algorithms function, inability to create personalized recommendations based on individual needs, and failure to integrate multiple elements into the decision-making process. This paper presents a new system using Explainable AI (XAI) technology to address these shortcomings, providing students with a simple source to discover careers matching their interests and skills. The system components include a comprehensive user profile analyzer, a hybrid recommendation engine combining rule-based eligibility filtering with machine learning, and an interactive explanation interface using SHAP and LIME. This combination allows users to make choices suited to their individual circumstances without lengthy career information analysis. The recommendation system achieved 87.3% accuracy and 92% user satisfaction, exceeding current commercial providers after testing with 1,200 simulated and 85 real student profiles. The explainable AI feature raised user trust by 45% compared to black-box systems. This research advances transparency in educational technology, providing a tool that helps students understand how recommendations are developed, increasing student agency in career decision-making. The system is modular and can be easily adapted to any educational board or geographic region, making it highly applicable in diverse educational systems including but not limited to India.