Analyzing and repairing concept drift adaptation in data stream classification

Data collected over time often exhibit changes in distribution, or concept drift, caused by changes in factors relevant to the classification task, e.g. weather conditions. Incorporating all relevant factors into the model may be able to capture these changes, however, this is usually not practical. Data stream based methods, which instead explicitly detect concept drift, have been shown to retain performance under unknown changing conditions. These methods adapt to concept drift by training a model to classify each distinct data distribution. However, we hypothesize that existing methods do not robustly handle real-world tasks, leading to adaptation errors where context is misidentified. Adaptation errors may cause a system to use a model which does not fit the current data, reducing performance. We propose a novel repair algorithm to identify and correct errors in concept drift adaptation. Evaluation on synthetic data shows that our proposed AiRStream system has higher performance than baseline methods, while is also better at capturing the dynamics of the stream. Evaluation on an air quality inference task shows AiRStream provides increased real-world performance compared to eight baseline methods. A case study shows that AiRStream is able to build a robust model of environmental conditions over this task, allowing the adaptions made to concept drift to be analysed and related to changes in weather. We discovered a strong predictive link between the adaptions made by AiRStream and changes in meteorological conditions.