Student Performance Prediction

Student performance prediction uses machine learning to forecast student success, aiming to identify at-risk students and personalize learning experiences. Current research emphasizes improving prediction accuracy and interpretability through various model architectures, including deep learning (e.g., neural networks, graph convolutional networks, recurrent neural networks), ensemble methods, and transfer learning, often incorporating explainable AI techniques to build trust and transparency. These advancements hold significant potential for enhancing educational interventions, optimizing resource allocation, and ultimately improving student outcomes across diverse learning environments.

Papers

August 2, 2022

Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning
Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio, Laura Cruz, Kerrie Douglas, Andrew Lan, Christopher Brinton
Mitigating Bias Student Model Student Performance Prediction Student Encoder

July 1, 2022

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs
Vinitra Swamy, Bahar Radmehr, Natasa Krco, Mirko Marras, Tanja Käser
High Explainability Black Box Explainable Machine Learning Student Performance Prediction Black Box Machine Learning Model Massive Open Online Course Explanation Performance

December 15, 2021

Student Performance Prediction

Papers

Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations

Graph-based Ensemble Machine Learning for Student Performance Prediction