Speed of Concept Drift
Kenichi YOSHIDA · 2022
We present a brute-force approach to analyze con-cept drift behind time sequence data. This approach, named SELECT, searches for the optimal length of training data to minimize error metrics. In other words, SELECT searches for the start point of a new concept from the input sequence. Unlike many related works, SELECT does not require a pre-specified error threshold to detect drift. This paper analyzes the effect of concept drift speed on the performance of SELECT and previous representative methods. The experimental results show that SELECT can improve the model performance. In addition, SELECT can detect concept drift earlier than a typical method that uses a pre-specified error threshold. These results show the effectiveness of the brute-force approach to analyzing concept drift.