Investigating AI-Supported Learning Analytics for Enhancing Developmental Outcomes of Students in Nigerian Schools: A Mixed-Methods Study

This study examined how AI-based learning analytics (LA) inform educators regarding students’ developmental needs and assess the predicted benefits and challenges within the Nigerian educational system. It employed two research questions, objectives and one hypothesis that offered a purposeful direction. The study utilised a convergent parallel mixed-methods research design. This design enabled the collection of quantitative survey data from 600 educators and students with qualitative data from semi-structured interviews and platform-generated analytics. The descriptive and inferential statistics were utilised for measuring the impact on instructional precision through Python algorithm. The NVivo was used to thematically explore stakeholders lived experiences. The analyses determined the effectiveness of predictive dashboards in flagging at-risk students and the role of machine-driven response toward reducing administrative workloads among educators. The findings offered that intermittent power supply, high data costs, and digital literacy gaps were the contextual barriers unique to the Nigerian schools. Through the triangulation of data sources, the finding further offered all-inclusive framework for integrating and optimising AI into West African secondary education. It was recommended that policymakers and educators should take advantage of utilising AI not only as a component of technological, but as a tool strategically enhancing holistic students’ developmental outcomes.