Salvato in:
Dettagli Bibliografici
Autori principali: Silva, Priscylla, Silva, Claudio T., Nonato, Luis Gustavo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.13957
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913359596617728
author Silva, Priscylla
Silva, Claudio T.
Nonato, Luis Gustavo
author_facet Silva, Priscylla
Silva, Claudio T.
Nonato, Luis Gustavo
contents Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these models' predictions, especially in explainability within education. This work addresses this gap by employing nine distinct explanation methods and conducting a comprehensive analysis to explore the correlation between the agreement among these methods in generating explanations and the predictive model's performance. Applying Spearman's correlation, our findings reveal a very strong correlation between the model's performance and the agreement level observed among the explanation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the Relationship Between Feature Attribution Methods and Model Performance
Silva, Priscylla
Silva, Claudio T.
Nonato, Luis Gustavo
Machine Learning
Machine learning and deep learning models are pivotal in educational contexts, particularly in predicting student success. Despite their widespread application, a significant gap persists in comprehending the factors influencing these models' predictions, especially in explainability within education. This work addresses this gap by employing nine distinct explanation methods and conducting a comprehensive analysis to explore the correlation between the agreement among these methods in generating explanations and the predictive model's performance. Applying Spearman's correlation, our findings reveal a very strong correlation between the model's performance and the agreement level observed among the explanation methods.
title Exploring the Relationship Between Feature Attribution Methods and Model Performance
topic Machine Learning
url https://arxiv.org/abs/2405.13957