IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2207.05701.html
   My bibliography  Save this paper

Autoencoding Conditional GAN for Portfolio Allocation Diversification

Author

Listed:
  • Jun Lu
  • Shao Yi

Abstract

Over the decades, the Markowitz framework has been used extensively in portfolio analysis though it puts too much emphasis on the analysis of the market uncertainty rather than on the trend prediction. While generative adversarial network (GAN) and conditional GAN (CGAN) have been explored to generate financial time series and extract features that can help portfolio analysis. The limitation of the CGAN framework stands in putting too much emphasis on generating series rather than keeping features that can help this generator. In this paper, we introduce an autoencoding CGAN (ACGAN) based on deep generative models that learns the internal trend of historical data while modeling market uncertainty and future trends. We evaluate the model on several real-world datasets from both the US and Europe markets, and show that the proposed ACGAN model leads to better portfolio allocation and generates series that are closer to true data compared to the existing Markowitz and CGAN approaches.

Suggested Citation

  • Jun Lu & Shao Yi, 2022. "Autoencoding Conditional GAN for Portfolio Allocation Diversification," Papers 2207.05701, arXiv.org.
    • Handle: RePEc:arx:papers:2207.05701
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2207.05701
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Timmermann, Allan & Granger, Clive W. J., 2004. "Efficient market hypothesis and forecasting," International Journal of Forecasting, Elsevier, vol. 20(1), pages 15-27.
    2. Takahashi, Shuntaro & Chen, Yu & Tanaka-Ishii, Kumiko, 2019. "Modeling financial time-series with generative adversarial networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 527(C).
    3. Daniel D. Lee & H. Sebastian Seung, 1999. "Learning the parts of objects by non-negative matrix factorization," Nature, Nature, vol. 401(6755), pages 788-791, October.
    4. Bollerslev, Tim, 1986. "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, Elsevier, vol. 31(3), pages 307-327, April.
    5. Giovanni Mariani & Yada Zhu & Jianbo Li & Florian Scheidegger & Roxana Istrate & Costas Bekas & A. Cristiano I. Malossi, 2019. "PAGAN: Portfolio Analysis with Generative Adversarial Networks," Papers 1909.10578, arXiv.org.
    6. Anirban Chakraborti & Ioane Muni Toke & Marco Patriarca & Frederic Abergel, 2011. "Econophysics review: I. Empirical facts," Quantitative Finance, Taylor & Francis Journals, vol. 11(7), pages 991-1012.
    7. R. Cont, 2001. "Empirical properties of asset returns: stylized facts and statistical issues," Quantitative Finance, Taylor & Francis Journals, vol. 1(2), pages 223-236.
    8. Anirban Chakraborti & Ioane Muni Toke & Marco Patriarca & Frédéric Abergel, 2011. "Econophysics review: I. Empirical facts," Post-Print hal-00621058, HAL.
    9. Florian Eckerli & Joerg Osterrieder, 2021. "Generative Adversarial Networks in finance: an overview," Papers 2106.06364, arXiv.org, revised Jul 2021.
    10. Jun Lu & Shao Yi, 2022. "Reducing overestimating and underestimating volatility via the augmented blending-ARCH model," Papers 2203.12456, arXiv.org.
    11. Tina Hviid Rydberg, 2000. "Realistic Statistical Modelling of Financial Data," International Statistical Review, International Statistical Institute, vol. 68(3), pages 233-258, December.
    12. Engle, Robert F, 1982. "Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation," Econometrica, Econometric Society, vol. 50(4), pages 987-1007, July.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Timothé Gronier & William Maréchal & Christophe Geissler & Stéphane Gibout, 2022. "Usage of GAMS-Based Digital Twins and Clustering to Improve Energetic Systems Control," Energies, MDPI, vol. 16(1), pages 1-17, December.
    2. Jos'e-Manuel Pe~na & Fernando Su'arez & Omar Larr'e & Domingo Ram'irez & Arturo Cifuentes, 2023. "A Modified CTGAN-Plus-Features Based Method for Optimal Asset Allocation," Papers 2302.02269, arXiv.org, revised May 2024.
    3. Jun Lu & Danny Ding, 2022. "A Hybrid Approach on Conditional GAN for Portfolio Analysis," Papers 2208.07159, arXiv.org.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jun Lu & Shao Yi, 2022. "Autoencoding Conditional GAN for Portfolio Allocation Diversification," Applied Economics and Finance, Redfame publishing, vol. 9(3), pages 55-68, August.
    2. Jun Lu & Danny Ding, 2022. "A Hybrid Approach on Conditional GAN for Portfolio Analysis," Papers 2208.07159, arXiv.org.
    3. Magnus Wiese & Robert Knobloch & Ralf Korn & Peter Kretschmer, 2019. "Quant GANs: Deep Generation of Financial Time Series," Papers 1907.06673, arXiv.org, revised Dec 2019.
    4. Inoua, Sabiou M. & Smith, Vernon L., 2023. "A classical model of speculative asset price dynamics," Journal of Behavioral and Experimental Finance, Elsevier, vol. 37(C).
    5. Xiaoyu Tan & Zili Zhang & Xuejun Zhao & Shuyi Wang, 2022. "DeepPricing: pricing convertible bonds based on financial time-series generative adversarial networks," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-38, December.
    6. Aleksejus Kononovicius & Julius Ruseckas, 2014. "Nonlinear GARCH model and 1/f noise," Papers 1412.6244, arXiv.org, revised Feb 2015.
    7. Andrea Di Iura & Giulia Terenzi, 2022. "A Bayesian analysis of gain-loss asymmetry," SN Business & Economics, Springer, vol. 2(5), pages 1-23, May.
    8. Desislava Chetalova & Thilo A. Schmitt & Rudi Schafer & Thomas Guhr, 2013. "Portfolio return distributions: Sample statistics with non-stationary correlations," Papers 1308.3961, arXiv.org, revised Jun 2014.
    9. Andrea Giuseppe Di Iura & Giulia Terenzi, 2021. "A Bayesian analysis of gain-loss asymmetry," Papers 2104.06044, arXiv.org.
    10. Gontis, V. & Havlin, S. & Kononovicius, A. & Podobnik, B. & Stanley, H.E., 2016. "Stochastic model of financial markets reproducing scaling and memory in volatility return intervals," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 462(C), pages 1091-1102.
    11. Kononovicius, A. & Ruseckas, J., 2015. "Nonlinear GARCH model and 1/f noise," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 427(C), pages 74-81.
    12. Vygintas Gontis & Shlomo Havlin & Aleksejus Kononovicius & Boris Podobnik & H. Eugene Stanley, 2015. "Stochastic model of financial markets reproducing scaling and memory in volatility return intervals," Papers 1507.05203, arXiv.org, revised Oct 2016.
    13. Ivivi Joseph Mwaniki, 2019. "Modeling heteroscedastic, skewed and leptokurtic returns in discrete time," Journal of Applied Finance & Banking, SCIENPRESS Ltd, vol. 9(5), pages 1-1.
    14. Paulo Jorge Silveira Ferreira, 2012. "Testing serial dependence in the stock markets of the G7 countries, Portugal, Spain and Greece," CEFAGE-UE Working Papers 2012_24, University of Evora, CEFAGE-UE (Portugal).
    15. Krenar Avdulaj & Ladislav Kristoufek, 2020. "On Tail Dependence and Multifractality," Mathematics, MDPI, vol. 8(10), pages 1-13, October.
    16. Andrea Coletta & Matteo Prata & Michele Conti & Emanuele Mercanti & Novella Bartolini & Aymeric Moulin & Svitlana Vyetrenko & Tucker Balch, 2021. "Towards Realistic Market Simulations: a Generative Adversarial Networks Approach," Papers 2110.13287, arXiv.org.
    17. Kovačić, Zlatko, 2007. "Forecasting volatility: Evidence from the Macedonian stock exchange," MPRA Paper 5319, University Library of Munich, Germany.
    18. Lallouache, Mehdi & Abergel, Frédéric, 2014. "Tick size reduction and price clustering in a FX order book," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 416(C), pages 488-498.
    19. Zou, Yongjie & Li, Honggang, 2014. "Time spans between price maxima and price minima in stock markets," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 395(C), pages 303-309.
    20. Kei Nakagawa & Yusuke Uchiyama, 2020. "GO-GJRSK Model with Application to Higher Order Risk-Based Portfolio," Mathematics, MDPI, vol. 8(11), pages 1-12, November.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2207.05701. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.