Explainable AI-Assisted Multi-Criteria Decision Support for Tutor Recommendation

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Manual tutor assignment in online tutoring marketplacesbecomes increasingly time-consuming, inconsistent,and challenging to scale as the number of available tutorsgrows. This paper proposes an Explainable AI-assisted Multi-Criteria Decision Support framework for tutor recommendation,developed and evaluated on the Hamro Tutor platform. Theframework combines a deterministic Multi-Criteria DecisionMaking (MCDM) engine, which first applies grade-level, subject,and gender eligibility filtering and then ranks eligible candidatetutors using weighted scoring across location, availability, budget,qualification, and teaching experience, with a Large LanguageModel (LLM)-based explainability layer that generates humanreadablejustifications for each recommendation. Unlike fullyautonomous recommendation systems, the proposed frameworkkeeps the human administrator in the decision loop, using AI tosupport rather than replace human judgment. The system wasevaluated on 10 real student tuition requests against a pool of 30tutors, comparing manual and AI-assisted assignment workflows.Results show that AI-assisted selection reduced average decisiontime from 240.4 seconds to 22.6 seconds per request, a reductionof approximately 90.6%. Three platform administrators ratedthe suitability of AI-recommended tutors at an average of 4.57out of 5, and rated the clarity of generated explanations at 4.77out of 5. These findings suggest that explainable, human-in-theloopAI decision support can meaningfully reduce administrativeeffort in tutor allocation while achieving positively perceivedrecommendation suitability and explanation quality.