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

Mrim M. Alnfiai (), Faiz Abdullah Alotaibi, Mona Mohammed Alnahari, Nouf Abdullah Alsudairy, Asma Ibrahim Alharbi and Saad Alzahrani
Additional contact information
Mrim M. Alnfiai: Taif University
Faiz Abdullah Alotaibi: King Saud University
Mona Mohammed Alnahari: Taif University
Nouf Abdullah Alsudairy: Imam Mohammad Ibn Saud Islamic University (IMSIU)
Asma Ibrahim Alharbi: King Saud University
Saad Alzahrani: King Saud University

Palgrave Communications, 2025, vol. 12, issue 1, 1-18

Abstract: Abstract 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

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1057/s41599-025-05187-y Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pal:palcom:v:12:y:2025:i:1:d:10.1057_s41599-025-05187-y

Ordering information: This journal article can be ordered from
https://www.nature.com/palcomms/about

DOI: 10.1057/s41599-025-05187-y

Access Statistics for this article

More articles in Palgrave Communications from Palgrave Macmillan
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().