Capturing Evolution Genes for Time Series Data
This work addresses time series prediction and explanation for applications involving user behavior analysis, but it appears incremental as it builds on existing concepts like adversarial generation.
The paper tackles the problem of modeling time series by capturing latent user behaviors through evolution genes, achieving an average improvement of +10.56% in F1 score on real-world datasets.
The modeling of time series is becoming increasingly critical in a wide variety of applications. Overall, data evolves by following different patterns, which are generally caused by different user behaviors. Given a time series, we define the evolution gene to capture the latent user behaviors and to describe how the behaviors lead to the generation of time series. In particular, we propose a uniform framework that recognizes different evolution genes of segments by learning a classifier, and adopt an adversarial generator to implement the evolution gene by estimating the segments' distribution. Experimental results based on a synthetic dataset and five real-world datasets show that our approach can not only achieve a good prediction results (e.g., averagely +10.56% in terms of F1), but is also able to provide explanations of the results.