Recurrent Neural Goodness-of-Fit Test for Time Series
This addresses a critical gap in evaluating generative models for time series data in domains like finance and healthcare, though it is an incremental improvement by applying existing statistical tests with a novel transformation method.
The paper tackles the challenge of evaluating generative time series models by proposing the RENAL Goodness-of-Fit test, a statistically rigorous framework that uses recurrent neural networks to transform data for chi-square testing, and demonstrates it outperforms existing methods in reliability and accuracy on synthetic and real-world datasets.
Time series data are crucial across diverse domains such as finance and healthcare, where accurate forecasting and decision-making rely on advanced modeling techniques. While generative models have shown great promise in capturing the intricate dynamics inherent in time series, evaluating their performance remains a major challenge. Traditional evaluation metrics fall short due to the temporal dependencies and potential high dimensionality of the features. In this paper, we propose the REcurrent NeurAL (RENAL) Goodness-of-Fit test, a novel and statistically rigorous framework for evaluating generative time series models. By leveraging recurrent neural networks, we transform the time series into conditionally independent data pairs, enabling the application of a chi-square-based goodness-of-fit test to the temporal dependencies within the data. This approach offers a robust, theoretically grounded solution for assessing the quality of generative models, particularly in settings with limited time sequences. We demonstrate the efficacy of our method across both synthetic and real-world datasets, outperforming existing methods in terms of reliability and accuracy. Our method fills a critical gap in the evaluation of time series generative models, offering a tool that is both practical and adaptable to high-stakes applications.