Conditional GAN for timeseries generation
This work addresses the challenge of data scarcity for machine learning applications in time series analysis, offering a solution for generating quality synthetic data, though it appears incremental as it builds on existing GAN methods.
The paper tackles the problem of generating realistic synthetic time series data with limited training data by proposing a new architecture called Time Series GAN (TSGAN). The results show that TSGAN outperforms competitors on 70 benchmark datasets, achieving better scores in both quantitative metrics like FID and qualitative classification evaluations.
It is abundantly clear that time dependent data is a vital source of information in the world. The challenge has been for applications in machine learning to gain access to a considerable amount of quality data needed for algorithm development and analysis. Modeling synthetic data using a Generative Adversarial Network (GAN) has been at the heart of providing a viable solution. Our work focuses on one dimensional times series and explores the few shot approach, which is the ability of an algorithm to perform well with limited data. This work attempts to ease the frustration by proposing a new architecture, Time Series GAN (TSGAN), to model realistic time series data. We evaluate TSGAN on 70 data sets from a benchmark time series database. Our results demonstrate that TSGAN performs better than the competition both quantitatively using the Frechet Inception Score (FID) metric, and qualitatively when classification is used as the evaluation criteria.