Explaining Drift using Shapley Values
This addresses the need for a principled explanation method for concept drift in machine learning, which is incremental as it builds on existing Shapley value techniques.
The paper tackles the problem of identifying the drivers behind model performance deterioration due to concept drift, proposing DBShap, a framework that uses Shapley values to quantify contributions of individual features and changes in input-output relations.
Machine learning models often deteriorate in their performance when they are used to predict the outcomes over data on which they were not trained. These scenarios can often arise in real world when the distribution of data changes gradually or abruptly due to major events like a pandemic. There have been many attempts in machine learning research to come up with techniques that are resilient to such Concept drifts. However, there is no principled framework to identify the drivers behind the drift in model performance. In this paper, we propose a novel framework - DBShap that uses Shapley values to identify the main contributors of the drift and quantify their respective contributions. The proposed framework not only quantifies the importance of individual features in driving the drift but also includes the change in the underlying relation between the input and output as a possible driver. The explanation provided by DBShap can be used to understand the root cause behind the drift and use it to make the model resilient to the drift.