Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback

Abstract Accurate prediction of student performance is essential for the creation of adaptive learning frameworks and the best utilization of educational strategies. In this work, we apply ensemble learning and neural networks to investigate data from multiple sources about students, two real educat...

Full description

Saved in:
Bibliographic Details
Main Authors: Hafiz Muhammad Qadir, M. Taseer Suleman, Rafaqat Alam Khan, Muhammad Sohaib, Md Junayed Hasan, Syed Abid Hussain
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Journal of Big Data
Online Access:https://doi.org/10.1186/s40537-025-01187-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137995988959232
author Hafiz Muhammad Qadir
M. Taseer Suleman
Rafaqat Alam Khan
Muhammad Sohaib
Md Junayed Hasan
Syed Abid Hussain
author_facet Hafiz Muhammad Qadir
M. Taseer Suleman
Rafaqat Alam Khan
Muhammad Sohaib
Md Junayed Hasan
Syed Abid Hussain
author_sort Hafiz Muhammad Qadir
collection DOAJ
description Abstract Accurate prediction of student performance is essential for the creation of adaptive learning frameworks and the best utilization of educational strategies. In this work, we apply ensemble learning and neural networks to investigate data from multiple sources about students, two real educational datasets from Kaggle, and two synthetically generated datasets. A Python-based generative script was used to create one synthetic dataset; another synthetic dataset is created by augmenting a smaller Kaggle dataset while keeping its original statistical distribution. The Integrated Synthetic Data will make the model more robust, mitigate class imbalance, and generalize predictively in a much better way across heterogeneous educational data. In this paper, we implement several ensemble models-AdaBoost, Gradient Boosting, XGBoost, LightGBM, and CatBoost-and deep learning architectures such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Recurrent Neural Networks (RNN). These models are evaluated using accuracy, precision, recall, F1-score, and ROC-AUC to assess their predictive effectiveness. Experimental results demonstrate that CatBoost outperforms other ensemble models with an accuracy of 0.7143 and an F1-score of 0.7338, while CNN achieves the highest performance for sequential data (accuracy: 0.6786). ROC-AUC analysis confirms CatBoost and XGBoost as top-performing classifiers, while CNN and DNN exhibit superior capability in handling temporal patterns. The study highlights the impact of dataset augmentation and synthetic data generation on improving predictive accuracy in educational data mining, reinforcing the importance of data-centric approaches for building intelligent, and evidence-driven educational systems. The learning feedback has been made available via a user-friendly webserver at: https://khan-learning-feedback.streamlit.app/ .
format Article
id doaj-art-48f7e8a48d224b70a15179769bdbdc34
institution OA Journals
issn 2196-1115
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Journal of Big Data
spelling doaj-art-48f7e8a48d224b70a15179769bdbdc342025-08-20T02:30:42ZengSpringerOpenJournal of Big Data2196-11152025-06-0112112610.1186/s40537-025-01187-6Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedbackHafiz Muhammad Qadir0M. Taseer Suleman1Rafaqat Alam Khan2Muhammad Sohaib3Md Junayed Hasan4Syed Abid Hussain5Department of Software Engineering, Lahore Garrison UniversityDepartment of Computer Science, Bahria University Lahore CampusDepartment of Software Engineering, Lahore Garrison UniversitySchool of Computer Science and Technology, Zhejiang Normal UniversityDataxenseDepartment of Computer Science and Engineering, Bakhtar UniversityAbstract Accurate prediction of student performance is essential for the creation of adaptive learning frameworks and the best utilization of educational strategies. In this work, we apply ensemble learning and neural networks to investigate data from multiple sources about students, two real educational datasets from Kaggle, and two synthetically generated datasets. A Python-based generative script was used to create one synthetic dataset; another synthetic dataset is created by augmenting a smaller Kaggle dataset while keeping its original statistical distribution. The Integrated Synthetic Data will make the model more robust, mitigate class imbalance, and generalize predictively in a much better way across heterogeneous educational data. In this paper, we implement several ensemble models-AdaBoost, Gradient Boosting, XGBoost, LightGBM, and CatBoost-and deep learning architectures such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Recurrent Neural Networks (RNN). These models are evaluated using accuracy, precision, recall, F1-score, and ROC-AUC to assess their predictive effectiveness. Experimental results demonstrate that CatBoost outperforms other ensemble models with an accuracy of 0.7143 and an F1-score of 0.7338, while CNN achieves the highest performance for sequential data (accuracy: 0.6786). ROC-AUC analysis confirms CatBoost and XGBoost as top-performing classifiers, while CNN and DNN exhibit superior capability in handling temporal patterns. The study highlights the impact of dataset augmentation and synthetic data generation on improving predictive accuracy in educational data mining, reinforcing the importance of data-centric approaches for building intelligent, and evidence-driven educational systems. The learning feedback has been made available via a user-friendly webserver at: https://khan-learning-feedback.streamlit.app/ .https://doi.org/10.1186/s40537-025-01187-6
spellingShingle Hafiz Muhammad Qadir
M. Taseer Suleman
Rafaqat Alam Khan
Muhammad Sohaib
Md Junayed Hasan
Syed Abid Hussain
Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
Journal of Big Data
title Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
title_full Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
title_fullStr Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
title_full_unstemmed Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
title_short Optimizing learning outcomes: a deep dive into hybrid AI models for adaptive educational feedback
title_sort optimizing learning outcomes a deep dive into hybrid ai models for adaptive educational feedback
url https://doi.org/10.1186/s40537-025-01187-6
work_keys_str_mv AT hafizmuhammadqadir optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback
AT mtaseersuleman optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback
AT rafaqatalamkhan optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback
AT muhammadsohaib optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback
AT mdjunayedhasan optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback
AT syedabidhussain optimizinglearningoutcomesadeepdiveintohybridaimodelsforadaptiveeducationalfeedback