Synthetic Time Series Generation via Complex Networks

TL;DR

This paper introduces a novel method for generating synthetic time series data using complex network mappings, specifically Quantile Graphs, which preserves statistical properties and offers an interpretable alternative to GANs.

Contribution

The paper proposes a new framework leveraging complex networks and Quantile Graphs for synthetic time series generation, demonstrating competitive performance and interpretability.

Findings

Quantile Graph-based method preserves statistical properties of original data.

The approach is competitive with state-of-the-art GAN methods.

Synthetic data maintains structural and statistical fidelity.

Abstract

Time series data are essential for a wide range of applications, particularly in developing robust machine learning models. However, access to high-quality datasets is often limited due to privacy concerns, acquisition costs, and labeling challenges. Synthetic time series generation has emerged as a promising solution to address these constraints. In this work, we present a framework for generating synthetic time series by leveraging complex networks mappings. Specifically, we investigate whether time series transformed into Quantile Graphs (QG) -- and then reconstructed via inverse mapping -- can produce synthetic data that preserve the statistical and structural properties of the original. We evaluate the fidelity and utility of the generated data using both simulated and real-world datasets, and compare our approach against state-of-the-art Generative Adversarial Network (GAN) methods. Results indicate that our quantile graph-based methodology offers a competitive and interpretable alternative for synthetic time series generation.