Model Drift in Deployed Machine Learning Models for Predicting Learning Success : научное издание

Kustitskaya Tatiana A.; Esin Roman V.; Noskov Mikhail V.

Дополнительные ссылки: eLibrary

База данных: Каталог библиотеки СФУ

Библиографическое описание: Model Drift in Deployed Machine Learning Models for Predicting Learning Success : научное издание / Tatiana A. Kustitskaya, Roman V. Esin, Mikhail V. Noskov. - Текст : непосредственный // Computers. - 2025. - Т. 14, № 9. - P. 351. - ISSN 2073-431X, DOI 10.3390/computers14090351.

Аннотация: The use of learning success prediction models is increasingly becoming a part of practice in educational institutions. While recent studies have primarily focused on the development of predictive models, the issue of their temporal stability remains underrepresented in the literature. This issue is critical as model drift can significantly reduce the effectiveness of Learning Analytics applications in real-world educational contexts. This study aims to identify effective approaches for assessing the degradation of predictive models in Learning Analytics and to explore retraining strategies to address model drift. We assess model drift in deployed academic success prediction models using statistical analysis, machine learning, and Explainable Artificial Intelligence. The findings indicate that students’ Digital Profile data are relatively stable, and models trained on these data exhibit minimal model drift, which can be effectively mitigated through regular retraining on more recent data. In contrast, Digital Footprint data from the LMS show moderate levels of data drift, and the models trained on them significantly degrade over time. The most effective strategy for mitigating model degradation involved training a more conservative model and excluding features that exhibited SHAP loss drift. However, this approach did not yield substantial improvements in model performance.

Год издания: 2025

Авторы: Kustitskaya Tatiana A. , Esin Roman V. , Noskov Mikhail V.

Источник: Computers

Выпуск: Т. 14, № 9

Номера страниц: 351

Держатель оригинала документа: School of Space and Information Technology, Siberian Federal University, 660041 Krasnoyarsk, Russia

Количество экземпляров:

Твёрдая копия издания отсутствует в фонде библиотеки

Показать дополнительные сведения

Hybrid Approach to Predicting Learning Success Based on Digital Educational History for Timely… : научное издание

Kustitskaya Tatiana A. и др.
2024 год

Predicting tree survival in agroforestry systems using machine learning classification algorithms : статья из журнала

Kravtsov Kirill и др.
2024 год

Predictive models and dynamics of estimates of applied tasks characteristics using machine… : статья из журнала

Konstantinov A. V.
2024 год

Machine learning in soil science for prediction and management of biological activity for… : статья из журнала

Kukartseva Svetlana и др.
2024 год

Predicting Diffusion Coefficients in Nafion Membranes during the Soaking Process Using a Machine… : статья из журнала

Malashin Ivan и др.
2024 год

Mathematical model for early prediction of learning success : доклад, тезисы доклада

Noskov Michail и др.
2024 год

Machine learning method for predicting line-shapes of Fano resonances induced by bound states in… : научное издание

Gerasimov V.S. и др.
2025 год

Interpretation methods for machine learning models in the framework of survival analysis with… : статья из журнала

Utkin L. V. и др.
2024 год

Machine learning model for the BIM classification in IFC format : статья из журнала

Petrochenko M. V. и др.
2024 год

Machine Learning for Data Mining: Improve Your Data Mining Capabilities with Advanced Predictive… : научное издание

Salcedo Jesus
2019 год

Estimation and Prediction of the Polymers’ Physical Characteristics Using the Machine Learning… : статья из журнала

Malashin Ivan Pavlovich и др.
2024 год

Application of machine learning algorithms for predicting agricultural crop yields : доклад, тезисы доклада, статья…

Kukartsev Vladislav и др.
2024 год

Machine Learning Quick Reference. Quick and Essential Machine Learning Hacks for Training Smart… : справочное издание

Kumar Rahul
2019 год

Assessing wildfire extents in Siberian forests using machine learning : научное издание

Malashin Ivan P. и др.
2025 год

Boosting-Based Machine Learning Applications in Polymer Science: A Review : научное издание

Malashin Ivan и др.
2025 год

Supercomputer resources management using machine learning methods under constraints : статья из журнала

Muliukha V. A. и др.
2024 год

Библиотечно-издательский комплекс СФУ

Model Drift in Deployed Machine Learning Models for Predicting Learning Success : научное издание
статья из журнала

Похожие публикации