# Detecting Interpretable Subgroup Drifts

arXiv: https://arxiv.org/abs/2408.14682 · HTML: https://mlsanity.com/paper/2408.14682/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 53 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 10 of 10)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning](https://mlsanity.com/paper/1904.05419/) (2019)
- [From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors](https://mlsanity.com/paper/2203.11070/) (2022)
- [Scikit-Multiflow: A Multi-output Streaming Framework](https://mlsanity.com/paper/1807.04662/) (2018)
- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [Reactive Soft Prototype Computing for Concept Drift Streams](https://mlsanity.com/paper/2007.05432/) (2020)
- [Auditing and Achieving Intersectional Fairness in Classification Problems](https://mlsanity.com/paper/1911.01468/) (2019)
- [Adaptive Bernstein Change Detector for High-Dimensional Data Streams](https://mlsanity.com/paper/2306.12974/) (2023)

## Abstract (arXiv)

The ability to detect and adapt to changes in data distributions is crucial to maintain the accuracy and reliability of machine learning models. Detection is generally approached by observing the drift of model performance from a global point of view. However, drifts occurring in (fine-grained) data subgroups may go unnoticed when monitoring global drift. We take a different perspective, and introduce methods for observing drift at the finer granularity of subgroups. Relevant data subgroups are identified during training and monitored efficiently throughout the model's life. Performance drifts in any subgroup are detected, quantified and characterized so as to provide an interpretable summary of the model behavior over time. Experimental results confirm that our subgroup-level drift analysis identifies drifts that do not show at the (coarser) global dataset level. The proposed approach provides a valuable tool for monitoring model performance in dynamic real-world applications, offering insights into the evolving nature of data and ultimately contributing to more robust and adaptive models.