Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review
Explainability and interpretability have emerged as essential considerations in machine learning, particularly as models become more complex and integral to a wide range of applications. In response to increasing concerns over opaque “black-box” solutions, the literature has seen a shift toward two...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/7/443 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850067406224883712 |
|---|---|
| author | Daniele Pelosi Diletta Cacciagrano Marco Piangerelli |
| author_facet | Daniele Pelosi Diletta Cacciagrano Marco Piangerelli |
| author_sort | Daniele Pelosi |
| collection | DOAJ |
| description | Explainability and interpretability have emerged as essential considerations in machine learning, particularly as models become more complex and integral to a wide range of applications. In response to increasing concerns over opaque “black-box” solutions, the literature has seen a shift toward two distinct yet often conflated paradigms: explainable AI (XAI), which refers to post hoc techniques that provide external explanations for model predictions, and interpretable AI, which emphasizes models whose internal mechanisms are understandable by design. Meanwhile, the phenomenon of concept and data drift—where models lose relevance due to evolving conditions—demands renewed attention. High-impact events, such as financial crises or natural disasters, have highlighted the need for robust interpretable or explainable models capable of adapting to changing circumstances. Against this backdrop, our systematic review aims to consolidate current research on explainability and interpretability with a focus on concept and data drift. We gather a comprehensive range of proposed models, available datasets, and other technical aspects. By synthesizing these diverse resources into a clear taxonomy, we intend to provide researchers and practitioners with actionable insights and guidance for model selection, implementation, and ongoing evaluation. Ultimately, this work aspires to serve as a practical roadmap for future studies, fostering further advancements in transparent, adaptable machine learning systems that can meet the evolving needs of real-world applications. |
| format | Article |
| id | doaj-art-47809542ddd84febbe2a82dceeb39065 |
| institution | DOAJ |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-47809542ddd84febbe2a82dceeb390652025-08-20T02:48:19ZengMDPI AGAlgorithms1999-48932025-07-0118744310.3390/a18070443Explainability and Interpretability in Concept and Data Drift: A Systematic Literature ReviewDaniele Pelosi0Diletta Cacciagrano1Marco Piangerelli2Computer Science Division, School of Science and Technology, University of Camerino, Via Madonna delle Carceri 7, 62032 Camerino, ItalyComputer Science Division, School of Science and Technology, University of Camerino, Via Madonna delle Carceri 7, 62032 Camerino, ItalyComputer Science Division, School of Science and Technology, University of Camerino, Via Madonna delle Carceri 7, 62032 Camerino, ItalyExplainability and interpretability have emerged as essential considerations in machine learning, particularly as models become more complex and integral to a wide range of applications. In response to increasing concerns over opaque “black-box” solutions, the literature has seen a shift toward two distinct yet often conflated paradigms: explainable AI (XAI), which refers to post hoc techniques that provide external explanations for model predictions, and interpretable AI, which emphasizes models whose internal mechanisms are understandable by design. Meanwhile, the phenomenon of concept and data drift—where models lose relevance due to evolving conditions—demands renewed attention. High-impact events, such as financial crises or natural disasters, have highlighted the need for robust interpretable or explainable models capable of adapting to changing circumstances. Against this backdrop, our systematic review aims to consolidate current research on explainability and interpretability with a focus on concept and data drift. We gather a comprehensive range of proposed models, available datasets, and other technical aspects. By synthesizing these diverse resources into a clear taxonomy, we intend to provide researchers and practitioners with actionable insights and guidance for model selection, implementation, and ongoing evaluation. Ultimately, this work aspires to serve as a practical roadmap for future studies, fostering further advancements in transparent, adaptable machine learning systems that can meet the evolving needs of real-world applications.https://www.mdpi.com/1999-4893/18/7/443explainabilityexplainable AIinterpretabilityinterpretable AIconcept driftdata drift |
| spellingShingle | Daniele Pelosi Diletta Cacciagrano Marco Piangerelli Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review Algorithms explainability explainable AI interpretability interpretable AI concept drift data drift |
| title | Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review |
| title_full | Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review |
| title_fullStr | Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review |
| title_full_unstemmed | Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review |
| title_short | Explainability and Interpretability in Concept and Data Drift: A Systematic Literature Review |
| title_sort | explainability and interpretability in concept and data drift a systematic literature review |
| topic | explainability explainable AI interpretability interpretable AI concept drift data drift |
| url | https://www.mdpi.com/1999-4893/18/7/443 |
| work_keys_str_mv | AT danielepelosi explainabilityandinterpretabilityinconceptanddatadriftasystematicliteraturereview AT dilettacacciagrano explainabilityandinterpretabilityinconceptanddatadriftasystematicliteraturereview AT marcopiangerelli explainabilityandinterpretabilityinconceptanddatadriftasystematicliteraturereview |