Skip to content

Research

Interests

  • Fair machine learning and AI
  • Student performance prediction

Supervision

  • Chunyang Fan, 6-month intern (2023)

Publication

Peer-reviewed journal papers

  • 2024: [published] Mélina Verger, Chunyang Fan, Sébastien Lallé, François Bouchet, Vanda Luengo. A Comprehensive Study on Evaluating and Mitigating Algorithmic Unfairness with the MADD Metric. Journal of Educational Data Mining, 16 (1), 365–409.
  • 2024: [in press] Mélina Verger, François Bouchet, Sébastien Lallé, Vanda Luengo. Discriminations intersectionnelles : approfondir l'évaluation de l'équité algorithmique. L'exemple de la prédiction de la réussite académique avec des données issues de cours en ligne. Revue STICEF (Sciences et technologies de l'information et de la communication pour l'éducation et la formation).

Peer-reviewed conference papers

  • 2024: [poster paper] Valdemar Švábenský, Mélina Verger, Maria Mercedes T. Rodrigo, Clarence James G. Monterozo, Ryan S. Baker, Miguel Zenon Nicanor Lerias Saavedra, Sébastien Lallé, Atsushi Shimada. Evaluating Algorithmic Bias in Models for Predicting Academic Performance of Filipino Students. 17th International Conference on Educational Data Mining (EDM 2024), July 2024, Atlanta, Georgia, USA. [code]

  • 2024: [long paper] Sébastien Lallé, François Bouchet, Mélina Verger, Vanda Luengo. Fairness of MOOC Completion Predictions Across Demographics and Contextual Variables. 25th International Conference on Artificial Intelligence in Education (AIED 2024), July 2024, Recife, Brazil. hal-04631556

  • 2023: [long paper] Mélina Verger, Sébastien Lallé, François Bouchet, Vanda Luengo. Is Your Model "MADD"? A Novel Metric to Evaluate Algorithmic Fairness for Predictive Student Models. 16th International Conference on Educational Data Mining (EDM 2023), July 2023, Bangalore, India. [code]

  • 2023: [long paper] Mélina Verger, François Bouchet, Sébastien Lallé, Vanda Luengo. Caractérisation et mesure des comportements discriminants des modèles prédictifs. 11ème Conférence sur les Environnements Informatiques pour l'Apprentissage Humain (EIAH 2023), June 2023, Brest, France. hal-04131676. [code]

  • 2022: [long paper] Mélina Verger. Investiguer la notion d'équité algorithmique dans les environnements informatiques pour l'apprentissage humain. 9ièmes RJC EIAH 2022 : Environnements Informatiques pour l’Apprentissage Humain, May 2022, Lille, France. hal-03678739

Peer-reviewed workshop papers

  • 2023: [long paper] Mélina Verger, Chunyang Fan, Sébastien Lallé, François Bouchet, Vanda Luengo. A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models. 1st International Tutorial and Workshop on Responsible Knowledge Discovery in Education (RKDE 2023) at ECML PKDD 2023, September 2023, Turino, Italy. [code]

Communication

  • 2022: [poster] NewInML at NeurIPS 2022, December 2022, Paris, France.
  • 2021: [report] Mélina Verger, Hugo Jair Escalante. Predicting students’ performance in online courses using multiple data sources. DOI: 10.48550/arXiv.2109.07903. The code and a Codalab challenge are available.