Navigating cognitive boundaries: the impact of CognifyNet AI-powered educational analytics on student improvement

Modern educational systems increasingly demand sophisticated analytical tools to assess and enhance student performance through personalized learning approaches. Yet, educational analytics models often lack comprehensive integration of behavioural, cognitive, and emotional insights, limiting their predictive accuracy and real-world applicability. While traditional machine learning approaches such as random forest and neural networks have been applied to educational data, they typically present trade-offs between interpretability and predictive capability, failing to capture student learning processes’ complex, multidimensional nature. This research introduces CognifyNet, a novel hybrid AI-driven educational analytics model that combines ensemble learning principles with deep neural network architectures to analyse student behaviours, cognitive patterns, and engagement levels through an innovative two-stage fusion mechanism. The model integrates random forest decision-making with multi-layer perceptron feature learning, incorporating sentiment analysis and advanced data processing pipelines to generate personalized learning trajectories while maintaining model transparency. Evaluated through rigorous 5-fold cross-validation on a comprehensive dataset of 1200 anonymized student records and validated across multiple educational platforms, including UCI Student Performance and Open University Learning Analytics datasets, CognifyNet demonstrates superior performance over conventional approaches, achieving 10.5% reduction in mean squared error and 83% reduction in mean absolute error compared to baseline random forest models, with statistical significance confirmed through paired t-tests (p