Grasynda: Graph-based Synthetic Time Series Generation

TL;DR

Grasynda is a novel graph-based method for generating synthetic time series data that improves forecasting accuracy by better preserving data properties compared to existing augmentation techniques.

Contribution

Introduces Grasynda, a graph-based approach converting time series into network structures for more effective data augmentation in forecasting tasks.

Findings

Outperforms existing augmentation methods across multiple datasets.

Consistently improves forecasting accuracy with neural networks.

Method and experiments are publicly available.

Abstract

Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. However, extensive datasets are not always available in real-world scenarios. Although many data augmentation methods exist, their limitations include the use of transformations that do not adequately preserve data properties. This paper introduces Grasynda, a novel graph-based approach for synthetic time series generation that: (1) converts univariate time series into a network structure using a graph representation, where each state is a node and each transition is represented as a directed edge; and (2) encodes their temporal dynamics in a transition probability matrix. We performed an extensive evaluation of Grasynda as a data augmentation method for time series forecasting. We use three neural network variations on six benchmark datasets. The results indicate that Grasynda consistently outperforms other time series data augmentation methods, including ones used in state-of-the-art time series foundation models. The method and all experiments are publicly available.