An explainable hybrid artificial intelligence framework for predicting academic success among international students

Academic attainment is an important reflection of student development and institutional performance, thus increasing the necessity of early identification of students at academic risk to provide timely support and assistance. Despite the fact that machine learning (ML) methods show significant promise in higher education analytics, many predictive models operate as black boxes, which raises the question of the uniqueness of the predictions made. The present research develops a new explanatory artificial intelligence (XAI) system based on the SHAP method that combines different machine learning approaches with a transparent interpretation of variables. The evaluation will be conducted on a publicly available dataset consisting of user data related to students' demographic situations and their academic performance, using different artificial intelligence and machine learning algorithms. We assessed the predictive quality of algorithms, their computational requirements, the importance of features, and SHAP explanations within the framework of a unified analytical system. The design helps in identifying the elements that relate factors to individual outcomes, which questions the sole reliance on end results. Therefore, it provides a basis for a better understanding of the academic assistance needed and for enhancing the transparency, accountability, and ethical standards of AI intervention in education.

Authors

Publication Details

Journal
Journal of International Students
Published
2026-11-17
DOI
https://doi.org/10.32674/admcxq87
Primary Topic
Online Learning and Analytics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An explainable hybrid artificial intelligence framework for predicting academic success among international students

Saroj Kumar Gupta, Santhi Muttipoll Dharmarajlu, Ajay Chakravarty, Prakash Kuppuswamy et al.
Journal of International Students
Online Learning and Analytics
article

An explainable hybrid artificial intelligence framework for predicting academic success among international students

Saroj Kumar Gupta, Santhi Muttipoll Dharmarajlu, Ajay Chakravarty, Prakash Kuppuswamy, Vijaya Ramineni, Phaneendra Kanakamedala, Preeti Nashier, Purushottam Kumar
article en

Abstract

Academic attainment is an important reflection of student development and institutional performance, thus increasing the necessity of early identification of students at academic risk to provide timely support and assistance. Despite the fact that machine learning (ML) methods show significant promise in higher education analytics, many predictive models operate as black boxes, which raises the question of the uniqueness of the predictions made. The present research develops a new explanatory artificial intelligence (XAI) system based on the SHAP method that combines different machine learning approaches with a transparent interpretation of variables. The evaluation will be conducted on a publicly available dataset consisting of user data related to students' demographic situations and their academic performance, using different artificial intelligence and machine learning algorithms. We assessed the predictive quality of algorithms, their computational requirements, the importance of features, and SHAP explanations within the framework of a unified analytical system. The design helps in identifying the elements that relate factors to individual outcomes, which questions the sole reliance on end results. Therefore, it provides a basis for a better understanding of the academic assistance needed and for enhancing the transparency, accountability, and ethical standards of AI intervention in education.

Journal of International StudentsVol. 16(21)
Online Learning and Analytics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon