SHELF: A Gender-Sensitive Hybrid AI Framework for Advancing Educational Equity in Underserved Regions

Aim/Purpose: AI-based recommendation systems frequently fail to serve women in low-resource educational environments effectively, as they neglect critical realities, such as time constraints, limited connectivity, and socio-cultural barriers. This paper proposes a hybrid ensemble AI framework that directly addresses these contextual realities by integrating algorithmic fairness, gender-aware personalization, and low-bandwidth adaptability into a unified, women-focused framework. Background: Although AI-driven personalized learning has advanced rapidly, existing systems lack gender sensitivity, transparency, and contextual adaptability, limiting their effectiveness in promoting inclusive education. Methodology: A Systematic Literature Review (SLR) of 50 peer-reviewed studies (2015-2025) was conducted to analyze research trends in AI-powered recommender systems, gender-focused education, emerging technologies, and explainable AI in educational contexts. Contribution: The key addition of the study is a conceptual ensemble hybrid AI framework, namely Sensitive Hybrid Ensemble for Learning Fairness (SHELF), which provides a comprehensive framework for simultaneously incorporating gender-sensitive learner profiling, bias-conscious recommendation, and low-bandwidth adaptability. Based on a systematic review of 50 studies, the framework provides an evidence-based solution to a critical gap in gender-blind AI-driven educational systems in underserved areas. Findings: Results show that 48% of studies focus on AI-based recommender systems, 19% on adaptive and fair conceptual models, 11% on gender-specific education, and 12% on emerging technologies such as IoT and edge computing. Systematic reviews and meta-analyses of educational recommendation systems account for 7% of studies, while only 3% address transparency and explainability, highlighting a major research gap. Recommendations for Practitioners: Educational stakeholders should adopt gender-aware, fair, and explainable AI systems to provide personalized learning and career guidance for women learners. Recommendation for Researchers: Future research should emphasize inclusive AI design, bias mitigation, contextual adaptability, and explainability in educational systems. Impact on Society: Gender-aware AI in education can enhance women’s access to learning, reduce digital inequality, and support inclusive societal development. Future Research: Further work should validate hybrid AI frameworks across diverse educational contexts and assess long-term impacts on women learners.