pith. machine review for the scientific record. sign in

arxiv: 2604.16182 · v1 · submitted 2026-04-17 · 💻 cs.LG · cs.AI

Recognition: unknown

Synthetic data in cryptocurrencies using generative models

Andr\'e Saimon S. Sousa, Frank Acasiete, Hugo Saba, Oscar M. Granados, Otto Pires, Val\'eria Loureiro da Silva

Authors on Pith no claims yet

Pith reviewed 2026-05-10 08:48 UTC · model grok-4.3

classification 💻 cs.LG cs.AI
keywords synthetic datacryptocurrencyconditional generative adversarial networkstime seriesLSTMfinancial modelinganomaly detectionprivacy
0
0 comments X

The pith

Conditional generative adversarial networks generate synthetic cryptocurrency price series that reproduce temporal patterns and preserve market trends.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes deep learning methods to create artificial versions of cryptocurrency price records, addressing privacy risks and access limits that come with real financial datasets. It trains a conditional generative adversarial network whose generator is an LSTM recurrent network and whose discriminator is a multilayer perceptron, producing new time series from learned patterns in actual market data. Tests on several different crypto-assets indicate that the outputs retain key temporal structures, overall trends, and dynamic behaviors. This synthetic data is positioned as a practical substitute that supports downstream tasks while avoiding the confidentiality and regulatory obstacles of live market records. The approach is further described as more computationally economical than heavier generative alternatives.

Core claim

A conditional generative adversarial network that pairs an LSTM-type recurrent generator with an MLP discriminator produces synthetic cryptocurrency price time series that remain statistically consistent with real data, reproducing relevant temporal patterns and preserving market trends and dynamics across multiple crypto-assets.

What carries the argument

Conditional Generative Adversarial Network (CGAN) with an LSTM recurrent generator and MLP discriminator, which adversarially learns to output time series that match the statistical features of observed cryptocurrency prices.

If this is right

  • Synthetic series can substitute for real records in market behavior analysis without exposing private financial information.
  • The generated data can be applied to anomaly detection tasks in cryptocurrency markets.
  • The method operates at lower computational cost than more complex generative models.
  • The same architecture works across different crypto-assets while maintaining pattern fidelity.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Institutions could share synthetic datasets for collaborative research while keeping actual trading records confidential.
  • The technique might be extended to generate plausible extreme-event scenarios that appear infrequently in historical data.
  • Predictive models for trading or risk assessment could be trained entirely on synthetic series to reduce regulatory exposure.

Load-bearing premise

The synthetic series produced by the CGAN are statistically consistent with real cryptocurrency data and therefore suitable for applications such as market behavior analysis and anomaly detection.

What would settle it

A quantitative comparison that shows large, statistically significant differences between the synthetic and real series on metrics such as autocorrelation structure, volatility clustering, or trend preservation would falsify the central claim.

Figures

Figures reproduced from arXiv: 2604.16182 by Andr\'e Saimon S. Sousa, Frank Acasiete, Hugo Saba, Oscar M. Granados, Otto Pires, Val\'eria Loureiro da Silva.

Figure 3
Figure 3. Figure 3: Cryptocurrencies evolution (2022-2025) 7 [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Volatility by periods characterized by high-frequency oscillations, with daily changes frequently swinging between +8% and -8%. This represents a risk-off sentiment where investors oscillated between viewing Bitcoin or other cryptocurrencies as an asset hedge, but at the same time, a speculative high-beta asset. The intraday volatility seen throughout March 2022 indicates several perspectives on cryptocurr… view at source ↗
Figure 6
Figure 6. Figure 6: Losses during training: BTC. 11 [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Losses during training: ETH. The [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Losses during training: XRP. The [PITH_FULL_IMAGE:figures/full_fig_p013_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Dispersion real vs generated - BTC. The [PITH_FULL_IMAGE:figures/full_fig_p014_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Dispersion real vs generated - ETH. The [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Dispersion real vs generated - XRP. The [PITH_FULL_IMAGE:figures/full_fig_p014_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Original series vs generated series: BTC - data first period. [PITH_FULL_IMAGE:figures/full_fig_p015_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Original series vs generated series: BTC - data second period. [PITH_FULL_IMAGE:figures/full_fig_p015_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Original series vs generated series: BTC - data third period. [PITH_FULL_IMAGE:figures/full_fig_p016_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Original series vs generated series: ETH - data first period. [PITH_FULL_IMAGE:figures/full_fig_p017_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Original series vs generated series: ETH - data second period. [PITH_FULL_IMAGE:figures/full_fig_p017_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Original series vs generated series: ETH - data third period. [PITH_FULL_IMAGE:figures/full_fig_p018_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Original series vs generated series: XRP - data first period. [PITH_FULL_IMAGE:figures/full_fig_p019_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Original series vs generated series: XRP - data second period. [PITH_FULL_IMAGE:figures/full_fig_p019_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Original series vs generated series: XRP - data third period. [PITH_FULL_IMAGE:figures/full_fig_p020_20.png] view at source ↗
read the 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes using Conditional Generative Adversarial Networks (CGANs) with an LSTM generator and MLP discriminator to generate synthetic cryptocurrency price time series. It claims this addresses privacy and access restrictions on real financial data, with experiments on different crypto-assets demonstrating reproduction of relevant temporal patterns and preservation of market trends and dynamics. The approach is presented as an efficient alternative to more complex generative methods for applications such as market behavior analysis and anomaly detection.

Significance. If the claims of statistical consistency and pattern preservation hold under quantitative scrutiny, the work could provide a practical contribution to synthetic data generation for sensitive financial time series. It would enable privacy-preserving research and modeling in cryptocurrency markets, where real data access is often limited, and its reported efficiency advantage could support broader adoption in analysis and detection tasks.

major comments (2)
  1. [Abstract] Abstract: the claim that the CGAN produces 'statistically consistent synthetic data' and is 'capable of reproducing relevant temporal patterns, preserving market trends and dynamics' is unsupported, as no quantitative results, statistical tests, error metrics, distribution comparisons, or evaluation details are provided.
  2. [Experiments] Experiments description: the high-level statement that experiments on different crypto-assets demonstrate pattern reproduction supplies no metrics for temporal consistency (e.g., autocorrelation functions, volatility clustering, moments of returns) or similarity measures (e.g., KS test, Wasserstein distance) against real data, which is load-bearing for the central empirical claim.
minor comments (1)
  1. The claim of 'lower computational cost compared to more complex generative approaches' would be strengthened by including at least a brief runtime or resource comparison.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments highlighting the need for stronger quantitative support. We agree that the current version lacks explicit metrics and will revise the manuscript to include them, thereby strengthening the empirical claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the CGAN produces 'statistically consistent synthetic data' and is 'capable of reproducing relevant temporal patterns, preserving market trends and dynamics' is unsupported, as no quantitative results, statistical tests, error metrics, distribution comparisons, or evaluation details are provided.

    Authors: We acknowledge that the abstract's claims currently lack direct quantitative backing in the manuscript. In the revised version, we will add specific statistical tests and metrics (Kolmogorov-Smirnov tests, autocorrelation functions, volatility clustering, moments of returns, and Wasserstein distances) to the experiments and update the abstract to reference these results, ensuring the claims are properly supported. revision: yes

  2. Referee: [Experiments] Experiments description: the high-level statement that experiments on different crypto-assets demonstrate pattern reproduction supplies no metrics for temporal consistency (e.g., autocorrelation functions, volatility clustering, moments of returns) or similarity measures (e.g., KS test, Wasserstein distance) against real data, which is load-bearing for the central empirical claim.

    Authors: We agree that the experiments section requires quantitative metrics to substantiate the central claims. We will expand this section with the suggested evaluations, including autocorrelation functions, volatility clustering, return moments for temporal consistency, and KS tests plus Wasserstein distances for distributional similarity, applied across the crypto-assets studied. revision: yes

Circularity Check

0 steps flagged

No circularity: purely empirical work with no derivations or self-referential reductions

full rationale

The manuscript describes an application of CGANs (LSTM generator + MLP discriminator) to cryptocurrency price series and asserts that experiments on multiple assets show reproduction of temporal patterns and preservation of trends/dynamics. No equations, derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided text. The central claim is an empirical assertion rather than a mathematical reduction; it does not reduce to its own inputs by construction. Absence of quantitative metrics is a validation gap but does not create circularity under the defined patterns.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that standard CGAN components can capture crypto market dynamics, plus typical deep learning training assumptions; no new entities are postulated.

free parameters (1)
  • GAN training hyperparameters
    Learning rates, batch sizes, and network architectures are implicitly tuned but unspecified in the abstract.
axioms (1)
  • domain assumption LSTM generator combined with MLP discriminator suffices to model temporal patterns in cryptocurrency prices
    Invoked in the description of the approach and experimental claims.

pith-pipeline@v0.9.0 · 5470 in / 1194 out tokens · 32182 ms · 2026-05-10T08:48:44.178156+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 3 canonical work pages · 1 internal anchor

  1. [1]

    Raghunathan, J

    T. Raghunathan, J. Reiter, and D. Rubin. Multiple imputation for statistical disclosure limitation.AI, 19, 2003

    2003

  2. [2]

    Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

    A. Radford, L. Metz, and S. Chintala. Journal of official statistics.arXiv:1511.06434, 2015

    work page internal anchor Pith review arXiv 2015

  3. [3]

    Goodfellow, J

    I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y . Bengio. Generative adversarial nets.Advances In Neural Information Processing Systems, 3:2672–2680, 2014

    2014

  4. [4]

    Feng Han, Xiaojuan Ma, and Jiheng Zhang. Simulating multi-asset classes prices using wasserstein generative adversarial network: A study of stocks, futures and cryptocurrency.Journal of Risk and Financial Management, 15(1), 2022

    2022

  5. [5]

    A. A. Almamoori and W. S. Bhaya. Hybrid deep learning approach utilizing rnn and lstm for the detection of ddos attacks within the bitcoin ecosystem.Ingénierie des Systèmes d’Information, 28(4):931–937, 2023

    2023

  6. [6]

    Sanjalawe and Salam R

    Yousef K. Sanjalawe and Salam R. Al-E’mari. Abnormal transactions detection in the ethereum network using semi-supervised generative adversarial networks.IEEE Access, 11:98516–98531, 2023

    2023

  7. [7]

    J. Y . Zhu, P. Krähenbühl, E. Shechtman, and A. A. Efros. Generative visual manipulation on the natural image manifold.In European Conference on Computer Vision, pages 597–613, 2016

    2016

  8. [8]

    Killoran, L

    N. Killoran, L. J. Lee, D. A. Delong, and B. J. Frey Duvenaud. Generating and designing dna with deep generative models.arXiv:1712.06148, 2017

    work page arXiv 2017

  9. [9]

    Kadurin, S

    A. Kadurin, S. Nikolenko, K. Khrabrov, A. Aliper, and A. Zhavoronkov. Generating and designing dna with deep generative models.Molecular pharmaceutics, 14(3098), 2017

    2017

  10. [10]

    Improved techniques for training gans, 2016

    Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. Improved techniques for training gans, 2016

    2016

  11. [11]

    NetGAN: Generating graphs via random walks

    Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, and Stephan Günnemann. NetGAN: Generating graphs via random walks. In Jennifer Dy and Andreas Krause, editors,Proceedings of the 35th International Conference on Machine Learning, volume 80 ofProceedings of Machine Learning Research, pages 610–619. PMLR, 10–15 Jul 2018

    2018

  12. [12]

    A survey of recent advances in quantum generative adversarial networks.Electronics, 12(4):856, 2023

    Tuan A Ngo, Tuyen Nguyen, and Truong Cong Thang. A survey of recent advances in quantum generative adversarial networks.Electronics, 12(4):856, 2023

    2023

  13. [13]

    A review of generative adversarial networks (gans) and its applications in a wide variety of disciplines: From medical to remote sensing.IEEE Access, 12:18330–18357, 2024

    Ankan Dash, Junyi Ye, and Guiling Wang. A review of generative adversarial networks (gans) and its applications in a wide variety of disciplines: From medical to remote sensing.IEEE Access, 12:18330–18357, 2024

    2024

  14. [14]

    Modeling financial time-series with generative adversarial networks.Physica A: Statistical Mechanics and its Applications, 527:121261, 2019

    Shuntaro Takahashi, Yu Chen, and Kumiko Tanaka-Ishii. Modeling financial time-series with generative adversarial networks.Physica A: Statistical Mechanics and its Applications, 527:121261, 2019

    2019

  15. [15]

    Data augmentation of high frequency financial data using generative adversarial network

    Yusuke Naritomi and Takanori Adachi. Data augmentation of high frequency financial data using generative adversarial network. page 641 – 648, 2020

    2020

  16. [16]

    Desensitized financial data generation based on generative adversarial network and differential privacy.Big Data Mining and Analytics, 8(1):103 – 117, 2025

    Fan Zhang, Luyao Wang, and Xinhong Zhang. Desensitized financial data generation based on generative adversarial network and differential privacy.Big Data Mining and Analytics, 8(1):103 – 117, 2025

    2025

  17. [17]

    Stock market prediction on high-frequency data using generative adversarial nets.Mathematical Problems in Engineering, 2018(1):4907423, 2018

    Xingyu Zhou, Zhisong Pan, Guyu Hu, Siqi Tang, and Cheng Zhao. Stock market prediction on high-frequency data using generative adversarial nets.Mathematical Problems in Engineering, 2018(1):4907423, 2018

    2018

  18. [18]

    Stock market prediction based on generative adversarial network.Procedia computer science, 147:400–406, 2019

    Kang Zhang, Guoqiang Zhong, Junyu Dong, Shengke Wang, and Yong Wang. Stock market prediction based on generative adversarial network.Procedia computer science, 147:400–406, 2019

    2019

  19. [19]

    Generating realistic stock market order streams

    Junyi Li, Xintong Wang, Yaoyang Lin, Arunesh Sinha, and Michael Wellman. Generating realistic stock market order streams. InProceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 727–734, 2020. 22 Synthetic Data in Cryptocurrencies

    2020

  20. [20]

    Fin-gan: forecasting and classifying financial time series via generative adversarial networks.Quantitative Finance, 24(2):175–199, 2024

    Milena Vuleti´c, Felix Prenzel, and Mihai Cucuringu. Fin-gan: forecasting and classifying financial time series via generative adversarial networks.Quantitative Finance, 24(2):175–199, 2024

    2024

  21. [21]

    A cwgan-gp-based multi-task learning model for consumer credit scoring.Expert Systems with Applications, 206:117650, 2022

    Yanzhe Kang, Liao Chen, Ning Jia, Wei Wei, Jiang Deng, and Haizhang Qian. A cwgan-gp-based multi-task learning model for consumer credit scoring.Expert Systems with Applications, 206:117650, 2022

    2022

  22. [22]

    Stock price manipulation detection using generative adversarial networks

    Teema Leangarun, Poj Tangamchit, and Suttipong Thajchayapong. Stock price manipulation detection using generative adversarial networks. In2018 IEEE symposium series on computational intelligence (SSCI), pages 2104–2111. IEEE, 2018

    2018

  23. [23]

    Using generative adversarial networks for improving classification effectiveness in credit card fraud detection.Information Sciences, 479:448–455, 2019

    Ugo Fiore, Alfredo De Santis, Francesca Perla, Paolo Zanetti, and Francesco Palmieri. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection.Information Sciences, 479:448–455, 2019

    2019

  24. [24]

    Fraud detection in financial statements using data mining and gan models.Expert Systems with Applications, 227:120144, 2023

    Seyyede Zahra Aftabi, Ali Ahmadi, and Saeed Farzi. Fraud detection in financial statements using data mining and gan models.Expert Systems with Applications, 227:120144, 2023

    2023

  25. [25]

    Granados, O

    O. Granados, O. García-Bedoya, and E. González. Gan+abm to simulate suspicious money laundering trajectories. IEEE International Conference On Data Mining Workshops (ICDMW), pages 262–269, 2024

    2024

  26. [26]

    Y . Yang, F. Nan, P. Yang, Q. Meng, Y . Xie, D. Zhang, and K. Muhammad. Gan-based semi-supervised learning approach for clinical decision support in health-iot platform.IEEE Access, 7(6):8048–8057, 2019

    2019

  27. [27]

    Beaulieu-Jones, Z

    B. Beaulieu-Jones, Z. Wu, C. Williams, R. Lee, S. Bhavnani, J. Byrd, and C. Greene. Privacy-preserving generative deep neural networks support clinical data sharing.Circulation: Cardiovascular Quality And Outcomes, 7(12), 2019

    2019

  28. [28]

    Sandfort, K

    V . Sandfort, K. Yan, P. Pickhardt, and R. Summers. Data augmentation using generative adversarial networks (cyclegan) to improve generalizability in ct segmentation tasks.Scientific Reports, (11), 2019

    2019

  29. [29]

    J. Yoon, J. Jordon, and M. Schaar. Gan-based semi-supervised learning approach for clinical decision support in health-iot platform.International Conference on Learning Representations, 2019

    2019

  30. [30]

    SRV Editora LTDA, 2021

    Rogério Ferreira.Deep learning. SRV Editora LTDA, 2021. E-book

    2021

  31. [31]

    LTC, Rio de Janeiro, 3 edition, 2021

    Stuart Russell and Peter Norvig.Inteligência Artificial. LTC, Rio de Janeiro, 3 edition, 2021

    2021

  32. [32]

    Alta Books, Rio de Janeiro, 2021

    Aurélien Géron.Mãos à Obra: Aprendizado de Máquina com Scikit-Learn, Keras & TensorFlow — Conceitos, Ferramentas e Técnicas para a Construção de Sistemas Inteligentes. Alta Books, Rio de Janeiro, 2021. E-book

    2021

  33. [33]

    Langr and V

    J. Langr and V . Bok.GANs in Action: Deep Learning with Generative Adversarial Networks. Manning Publications, 2019

    2019

  34. [34]

    Goodfellow, Y

    I. Goodfellow, Y . Bengio, and A. Courville.Deep Learning. MIT Press, 2016

    2016

  35. [35]

    Recent progress on generative adversarial networks (gans): A survey.IEEE Access, 7:36322–36333, 2019

    Zhaoqing Pan, Weijie Yu, Xiaokai Yi, Asifullah Khan, Feng Yuan, and Yuhui Zheng. Recent progress on generative adversarial networks (gans): A survey.IEEE Access, 7:36322–36333, 2019

    2019

  36. [36]

    Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio

    Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. InProceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2, NIPS’14, page 2672–2680, Cambridge, MA, USA, 2014. MIT Press

    2014

  37. [37]

    Lipton, Mu Li, and Alexander J

    Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola.Dive into Deep Learning. Cambridge University Press, 2023

    2023

  38. [38]

    Integrated attentive bi-lstm conditional gan for power system oscillation localization.Electric Power Systems Research, 242, May 2025

    Lokesh Saravana, Quang-Ha Ngo, Jianhua Zhang, Tuyen Vu, and Thanh Long Vu b. Integrated attentive bi-lstm conditional gan for power system oscillation localization.Electric Power Systems Research, 242, May 2025

    2025

  39. [39]

    Kingma and Jimmy Ba

    Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization.International Conference on Learning Representations, 2015

    2015

  40. [40]

    Pytorch: An imperative style, high-performance deep learning library.Advances in Neural Information Processing Systems, 32, 2019

    Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. Pytorch: An imperative style, high-perfo...

    2019

  41. [41]

    The inefficiency of bitcoin.Economics Letters, 148:80–82, 2016

    Andrew Urquhart. The inefficiency of bitcoin.Economics Letters, 148:80–82, 2016

    2016

  42. [42]

    V olatility estimation for bitcoin: A comparison of garch models.Economics Letters, 158:3–6, 2017

    Paraskevi Katsiampa. V olatility estimation for bitcoin: A comparison of garch models.Economics Letters, 158:3–6, 2017. 23 Synthetic Data in Cryptocurrencies

    2017

  43. [43]

    Cryptocurrency forecasting with deep learning chaotic neural networks.Chaos, Solitons & Fractals, 118:35–40, 2019

    Salim Lahmiri and Stelios Bekiros. Cryptocurrency forecasting with deep learning chaotic neural networks.Chaos, Solitons & Fractals, 118:35–40, 2019

    2019

  44. [44]

    Quant gans: Deep generation of financial time series.Quantitative Finance, 20(9):1419–1440, 2020

    Magnus Wiese, Robert Knobloch, Ralf Korn, and Peter Kretschmer. Quant gans: Deep generation of financial time series.Quantitative Finance, 20(9):1419–1440, 2020

    2020

  45. [45]

    Time-series generative adversarial networks.Advances in Neural Information Processing Systems, 32:5508–5518, 2019

    Jinsung Yoon, Daniel Jarrett, and Mihaela van der Schaar. Time-series generative adversarial networks.Advances in Neural Information Processing Systems, 32:5508–5518, 2019

    2019

  46. [46]

    Forecasting cryptocurrency prices using deep learning.Finance Research Letters, 41:101798, 2021

    Yuchen Zhang et al. Forecasting cryptocurrency prices using deep learning.Finance Research Letters, 41:101798, 2021

    2021

  47. [47]

    Unsupervised representation learning with deep convolutional generative adversarial networks.International Conference on Learning Representations, 2016

    Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks.International Conference on Learning Representations, 2016

    2016

  48. [48]

    Real-valued (medical) time series generation with recurrent conditional gans.arXiv preprint arXiv:1706.02633, 2017

    Cristóbal Esteban, Stephanie L. Hyland, and Gunnar Rätsch. Real-valued (medical) time series generation with recurrent conditional gans.arXiv preprint arXiv:1706.02633, 2017. 24

    work page arXiv 2017