Control and Monitoring of Artificial Intelligence Algorithms
It tackles the issue of model reliability in real-world applications for practitioners, but is incremental as it builds on existing drift concepts.
The paper addresses the problem of monitoring AI models after deployment to detect data and concept drift, introducing metrics to assess performance changes over time, but does not provide concrete numerical results.
This paper elucidates the importance of governing an artificial intelligence model post-deployment and overseeing potential fluctuations in the distribution of present data in contrast to the training data. The concepts of data drift and concept drift are explicated, along with their respective foundational distributions. Furthermore, a range of metrics is introduced, which can be utilized to scrutinize the model's performance concerning potential temporal variations.