Authors: Elaf Abu Amrieh (Graduate Student), Thair Hamtini, Ibrahim Aljarah

In the research paper "Mining Educational Data to Predict Student’s Academic Performance Using Ensemble Methods," Elaf Abu Amrieh, a dedicated graduate student, collaborated with Dr. Ibrahim Aljarah to explore the application of advanced data mining techniques in predicting students' academic outcomes. The study highlights the innovative use of ensemble learning methods to enhance the accuracy of predictions and provide actionable insights for improving educational strategies.

This work represents a significant contribution by Elaf Abu Amrieh as a graduate researcher, showcasing her ability to handle complex datasets and apply cutting-edge machine learning techniques under the guidance of her academic mentors. The research delves into analyzing key academic factors—such as attendance, participation, and prior performance—while leveraging ensemble methods like bagging, boosting, and stacking to improve prediction reliability.

Key contributions of the research include:

1. Graduate-Led Initiative: Elaf Abu Amrieh's active involvement in data collection, preprocessing, and model implementation demonstrates the impactful role of graduate students in advancing educational data mining research.
2. Methodological Advancement: The team established that ensemble methods surpass traditional classifiers in predicting academic performance, providing a robust framework for educational analytics​​.
3. Implications for Education: The findings offer educators and policymakers tools to identify at-risk students and tailor interventions, improving educational outcomes on an institutional level.

This study stands as a testament to the potential of graduate students, like Elaf Abu Amrieh, to make meaningful contributions to scientific research, especially when supported by collaborative mentorship and a focus on addressing real-world challenges in education.

-----------------------------------------------------------------------

Student Paper:​

Title: Preprocessing and Analyzing Educational Data Set Using X-API for Improving Student's Performance

Authors: Elaf Abu Amrieh (Graduate Student), Thair Hamtini, Ibrahim Aljarah

Publication Date: November 3, 2015

Conference: 2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)

Pages: 1–5

Publisher: IEEE

Abstract:

This research paper explores the role of data preprocessing and feature analysis in predicting student performance by utilizing behavioral features extracted from the Experience API (X-API) on the Kalboard 360 e-learning system. By applying machine learning classifiers, including Artificial Neural Networks, Naïve Bayes, and Decision Trees, the study demonstrates how learner behaviors—captured via the e-learning platform—correlate strongly with academic achievements

Key Contributions:

Focus on Behavioral Data: The paper emphasizes the importance of using learner interaction data from the Kalboard 360 system to better understand factors influencing student performance.

Comprehensive Data Preprocessing: The authors detail a rigorous preprocessing approach to clean and prepare data for accurate modeling, highlighting its critical role in improving the performance of machine learning algorithms.

Model Evaluation: Classifiers such as Artificial Neural Networks, Naïve Bayes, and Decision Trees were tested, showcasing high accuracy in predicting academic outcomes based on behavioral features.

Practical Implications: The results indicate that analyzing behavioral data can help educators identify struggling students early, allowing for timely interventions to enhance learning outcomes.

Significance:

This paper, led by graduate student Elaf Abu Amrieh under the mentorship of Dr. Ibrahim Aljarah, provides a novel framework for utilizing X-API data to predict student performance. It highlights the growing importance of educational data mining in advancing personalized and data-driven learning methodologies. Published by IEEE, this work has implications for improving e-learning systems and fostering better academic support mechanisms.​