Causal Explanation of Concept Drift -- A Truly Actionable Approach
This work addresses the need for actionable explanations of concept drift to prevent model failures and errors in real-world applications like industrial manufacturing, though it appears incremental by building on existing model-based approaches.
The paper tackled the problem of explaining concept drift in machine learning systems by extending model-based drift explanations to causal explanations, resulting in a framework that isolates causally relevant features for targeted interventions.
In a world that constantly changes, it is crucial to understand how those changes impact different systems, such as industrial manufacturing or critical infrastructure. Explaining critical changes, referred to as concept drift in the field of machine learning, is the first step towards enabling targeted interventions to avoid or correct model failures, as well as malfunctions and errors in the physical world. Therefore, in this work, we extend model-based drift explanations towards causal explanations, which increases the actionability of the provided explanations. We evaluate our explanation strategy on a number of use cases, demonstrating the practical usefulness of our framework, which isolates the causally relevant features impacted by concept drift and, thus, allows for targeted intervention.