Synthetic data in cryptocurrencies using generative models
André Saimon S. Sousa, Otto Pires, Frank Acasiete, Oscar M. Granados, Valéria Loureiro da Silva + 1 more
TLDR
This paper proposes using Conditional GANs with LSTMs to generate realistic synthetic cryptocurrency price data, addressing privacy and access issues.
Key contributions
- Proposes a CGAN-based deep learning model for generating synthetic cryptocurrency price time series.
- Utilizes an LSTM generator and MLP discriminator to capture complex market dynamics and trends.
- Demonstrates the model's ability to reproduce relevant temporal patterns and market behavior.
- Offers an efficient, lower-cost alternative for financial data simulation, useful for analysis and anomaly detection.
Why it matters
Real financial data has privacy and access limitations. This work provides a novel, efficient way to generate synthetic crypto data, enabling safer research and development. It opens doors for market analysis and anomaly detection without compromising sensitive information.
Original Abstract
Data plays a fundamental role in consolidating markets, services, and products in the digital financial ecosystem. However, the use of real data, especially in the financial context, can lead to privacy risks and access restrictions, affecting institutions, research, and modeling processes. Although not all financial datasets present such limitations, this work proposes the use of deep learning techniques for generating synthetic data applied to cryptocurrency price time series. The approach is based on Conditional Generative Adversarial Networks (CGANs), combining an LSTM-type recurrent generator and an MLP discriminator to produce statistically consistent synthetic data. The experiments consider different crypto-assets and demonstrate that the model is capable of reproducing relevant temporal patterns, preserving market trends and dynamics. The generation of synthetic series through GANs is an efficient alternative for simulating financial data, showing potential for applications such as market behavior analysis and anomaly detection, with lower computational cost compared to more complex generative approaches.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.