Multilayer Concept Drift Detection Method Based on Model Explainability
Timely detection of concept drift plays a vital role in ensuring the stability and reliability of data-driven models. However, existing concept drift detection methods face challenges in achieving a proper balance between accuracy and timeliness while also disregarding the precise localization of th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10802879/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850100773650694144 |
|---|---|
| author | Haolan Zhang Xinyi Chen Min Hu Vijayan Sugumaran |
| author_facet | Haolan Zhang Xinyi Chen Min Hu Vijayan Sugumaran |
| author_sort | Haolan Zhang |
| collection | DOAJ |
| description | Timely detection of concept drift plays a vital role in ensuring the stability and reliability of data-driven models. However, existing concept drift detection methods face challenges in achieving a proper balance between accuracy and timeliness while also disregarding the precise localization of the drift point. To address these issues, this paper presents a novel three-layer drift detection algorithm named Hierarchical Concept Drift Detection based on SHapley Additive exPlanations (HCDD-SHAP). Initially, concept drift is identified by monitoring changes in the error rate, ensuring the promptness of drift detection. Subsequently, the SHAP method is incorporated to assess the features’ contribution to drift, thereby enhancing the precision of drift detection. Lastly, a drift point backtracking mechanism is introduced to accurately pinpoint the initial drift point, facilitating the rapid creation of new models. Experiments show that HCDD-SHAP exhibits superior performance on synthetic and real-world datasets, surpassing conventional drift detectors in terms of precision, recall, and detection delay across diverse detection scenarios. Additionally, in the context of a shield construction project, HCDD-SHAP demonstrates its ability to swiftly identify variations in dynamic engineering conditions, which underscores the considerable advantage of the proposed algorithm in scenarios that require real-time monitoring and control. |
| format | Article |
| id | doaj-art-9c33f9df982748079eb1d862b8fdc33a |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-9c33f9df982748079eb1d862b8fdc33a2025-08-20T02:40:13ZengIEEEIEEE Access2169-35362024-01-011219079119080810.1109/ACCESS.2024.351769710802879Multilayer Concept Drift Detection Method Based on Model ExplainabilityHaolan Zhang0Xinyi Chen1https://orcid.org/0009-0005-9648-0196Min Hu2https://orcid.org/0000-0003-2353-1923Vijayan Sugumaran3https://orcid.org/0000-0003-2557-3182SHU-UTS SILC Business School, Shanghai University, Shanghai, ChinaSHU-UTS SILC Business School, Shanghai University, Shanghai, ChinaSHU-UTS SILC Business School, Shanghai University, Shanghai, ChinaSchool of Business Administration, Oakland University, Rochester, MI, USATimely detection of concept drift plays a vital role in ensuring the stability and reliability of data-driven models. However, existing concept drift detection methods face challenges in achieving a proper balance between accuracy and timeliness while also disregarding the precise localization of the drift point. To address these issues, this paper presents a novel three-layer drift detection algorithm named Hierarchical Concept Drift Detection based on SHapley Additive exPlanations (HCDD-SHAP). Initially, concept drift is identified by monitoring changes in the error rate, ensuring the promptness of drift detection. Subsequently, the SHAP method is incorporated to assess the features’ contribution to drift, thereby enhancing the precision of drift detection. Lastly, a drift point backtracking mechanism is introduced to accurately pinpoint the initial drift point, facilitating the rapid creation of new models. Experiments show that HCDD-SHAP exhibits superior performance on synthetic and real-world datasets, surpassing conventional drift detectors in terms of precision, recall, and detection delay across diverse detection scenarios. Additionally, in the context of a shield construction project, HCDD-SHAP demonstrates its ability to swiftly identify variations in dynamic engineering conditions, which underscores the considerable advantage of the proposed algorithm in scenarios that require real-time monitoring and control.https://ieeexplore.ieee.org/document/10802879/Concept driftdrift detectionmodel explainabilitySHapley additive exPlanations |
| spellingShingle | Haolan Zhang Xinyi Chen Min Hu Vijayan Sugumaran Multilayer Concept Drift Detection Method Based on Model Explainability IEEE Access Concept drift drift detection model explainability SHapley additive exPlanations |
| title | Multilayer Concept Drift Detection Method Based on Model Explainability |
| title_full | Multilayer Concept Drift Detection Method Based on Model Explainability |
| title_fullStr | Multilayer Concept Drift Detection Method Based on Model Explainability |
| title_full_unstemmed | Multilayer Concept Drift Detection Method Based on Model Explainability |
| title_short | Multilayer Concept Drift Detection Method Based on Model Explainability |
| title_sort | multilayer concept drift detection method based on model explainability |
| topic | Concept drift drift detection model explainability SHapley additive exPlanations |
| url | https://ieeexplore.ieee.org/document/10802879/ |
| work_keys_str_mv | AT haolanzhang multilayerconceptdriftdetectionmethodbasedonmodelexplainability AT xinyichen multilayerconceptdriftdetectionmethodbasedonmodelexplainability AT minhu multilayerconceptdriftdetectionmethodbasedonmodelexplainability AT vijayansugumaran multilayerconceptdriftdetectionmethodbasedonmodelexplainability |