# Fiaingen: A financial time series generative method matching real-world data quality

arXiv: https://arxiv.org/abs/2510.01169 · HTML: https://mlsanity.com/paper/2510.01169/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [Conditional GAN for timeseries generation](https://mlsanity.com/paper/2006.16477/) (2020)
- [TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series](https://mlsanity.com/paper/2305.11567/) (2023)
- [TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers](https://mlsanity.com/paper/2307.12667/) (2023)
- [Time Series Analysis via Network Science: Concepts and Algorithms](https://mlsanity.com/paper/2110.09887/) (2021)
- [Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review](https://mlsanity.com/paper/2401.10370/) (2024)
- [Beyond Monte Carlo: Harnessing Diffusion Models to Simulate Financial Market Dynamics](https://mlsanity.com/paper/2412.00036/) (2024)

## Abstract (arXiv)

Data is vital in enabling machine learning models to advance research and practical applications in finance, where accurate and robust models are essential for investment and trading decision-making. However, real-world data is limited despite its quantity, quality, and variety. The data shortage of various financial assets directly hinders the performance of machine learning models designed to trade and invest in these assets. Generative methods can mitigate this shortage. In this paper, we introduce a set of novel techniques for time series data generation (we name them Fiaingen) and assess their performance across three criteria: (a) overlap of real-world and synthetic data on a reduced dimensionality space, (b) performance on downstream machine learning tasks, and (c) runtime performance. Our experiments demonstrate that the methods achieve state-of-the-art performance across the three criteria listed above. Synthetic data generated with Fiaingen methods more closely mirrors the original time series data while keeping data generation time close to seconds - ensuring the scalability of the proposed approach. Furthermore, models trained on it achieve performance close to those trained with real-world data.