November 20, 2025Big Data and Cognitive ComputingOpen Access

Interpretable Predictive Modeling for Educational Equity: A Workload-Aware Decision Support System for Early Identification of At-Risk Students

View Full Paper

Ask AI

Bookmark

Authors

ASAigul Shaikhanova OKOleksandr Kuznetsov KIKainizhamal Iklassova

Discussion

Member takes

Implication

Decision support system reveals that machine learning models can predict early disengagement in at-risk students, indicating improved educational equity outcomes.

Key Points

Gradient boosting achieved an AUC of 0.789 for early identification of at-risk students, emphasizing effective predictive modeling.
Logistic regression performed similarly with an AUC of 0.783, suggesting interpretable models can maintain performance accuracy.
The decision support system incorporates feature importance modeling with behavioral engagement prioritized over demographics.
Educational equity is advanced by a system that supports timely interventions while balancing instructor workload and model transparency.

Cite This Study

Shaikhanova et al. (2025) studied this question.

synapsesocial.com/papers/6924f07fc0ce034ddc350132 https://doi.org/10.3390/bdcc9110297

View Full Paper

Ask AI

Bookmark

Implication

Decision support system reveals that machine learning models can predict early disengagement in at-risk students, indicating improved educational equity outcomes.

Interpretable Predictive Modeling for Educational Equity: A Workload-Aware Decision Support System for Early Identification of At-Risk Students

Discussion

Member takes

Implication

Key Points

Cite This Study

Interpretable Predictive Modeling for Educational Equity: A Workload-Aware Decision Support System for Early Identification of At-Risk Students

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider