IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2407.15532.html
   My bibliography  Save this paper

Large-scale Time-Varying Portfolio Optimisation using Graph Attention Networks

Author

Listed:
  • Kamesh Korangi
  • Christophe Mues
  • Cristi'an Bravo

Abstract

Apart from assessing individual asset performance, investors in financial markets also need to consider how a set of firms performs collectively as a portfolio. Whereas traditional Markowitz-based mean-variance portfolios are widespread, network-based optimisation techniques have built upon these developments. However, most studies do not contain firms at risk of default and remove any firms that drop off indices over a certain time. This is the first study to incorporate risky firms and use all the firms in portfolio optimisation. We propose and empirically test a novel method that leverages Graph Attention networks (GATs), a subclass of Graph Neural Networks (GNNs). GNNs, as deep learning-based models, can exploit network data to uncover nonlinear relationships. Their ability to handle high-dimensional features and accommodate customised layers for specific purposes makes them particularly appealing for large-scale problems such as mid- and small-cap portfolio optimization. This study utilises 30 years of data on mid-cap firms, creating graphs of firms using distance correlation and the Triangulated Maximally Filtered Graph approach. These graphs are the inputs to a GAT model that we train using custom layers which impose weight and allocation constraints and a loss function derived from the Sharpe ratio, thus directly maximising portfolio risk-adjusted returns. This new model is benchmarked against a network characteristic-based portfolio, a mean variance-based portfolio, and an equal-weighted portfolio. The results show that the portfolio produced by the GAT-based model outperforms all benchmarks and is consistently superior to other strategies over a long period while also being informative of market dynamics.

Suggested Citation

  • Kamesh Korangi & Christophe Mues & Cristi'an Bravo, 2024. "Large-scale Time-Varying Portfolio Optimisation using Graph Attention Networks," Papers 2407.15532, arXiv.org.
  • Handle: RePEc:arx:papers:2407.15532
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2407.15532
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Diebold, Francis X. & Yilmaz, Kamil, 2012. "Better to give than to receive: Predictive directional measurement of volatility spillovers," International Journal of Forecasting, Elsevier, vol. 28(1), pages 57-66.
    2. R. Mantegna, 1999. "Hierarchical structure in financial markets," The European Physical Journal B: Condensed Matter and Complex Systems, Springer;EDP Sciences, vol. 11(1), pages 193-197, September.
    3. Jianqing Fan & Yuan Liao & Martina Mincheva, 2013. "Large covariance estimation by thresholding principal orthogonal complements," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 75(4), pages 603-680, September.
    4. Diebold, Francis X. & Yılmaz, Kamil, 2014. "On the network topology of variance decompositions: Measuring the connectedness of financial firms," Journal of Econometrics, Elsevier, vol. 182(1), pages 119-134.
    5. Farinelli, Simone & Ferreira, Manuel & Rossello, Damiano & Thoeny, Markus & Tibiletti, Luisa, 2008. "Beyond Sharpe ratio: Optimal asset allocation using different performance ratios," Journal of Banking & Finance, Elsevier, vol. 32(10), pages 2057-2063, October.
    6. Victor DeMiguel & Lorenzo Garlappi & Raman Uppal, 2009. "Optimal Versus Naive Diversification: How Inefficient is the 1-N Portfolio Strategy?," The Review of Financial Studies, Society for Financial Studies, vol. 22(5), pages 1915-1953, May.
    7. Bian, Zhicun & Liao, Yin & O’Neill, Michael & Shi, Jing & Zhang, Xueyong, 2020. "Large-scale minimum variance portfolio allocation using double regularization," Journal of Economic Dynamics and Control, Elsevier, vol. 116(C).
    8. P. Bonami & M. A. Lejeune, 2009. "An Exact Solution Approach for Portfolio Optimization Problems Under Stochastic and Integer Constraints," Operations Research, INFORMS, vol. 57(3), pages 650-670, June.
    9. Doron Avramov & Si Cheng & Lior Metzker, 2023. "Machine Learning vs. Economic Restrictions: Evidence from Stock Return Predictability," Management Science, INFORMS, vol. 69(5), pages 2587-2619, May.
    10. Arenas Parra, M. & Bilbao Terol, A. & Rodriguez Uria, M. V., 2001. "A fuzzy goal programming approach to portfolio selection," European Journal of Operational Research, Elsevier, vol. 133(2), pages 287-297, January.
    11. Andre F. Perold, 1984. "Large-Scale Portfolio Optimization," Management Science, INFORMS, vol. 30(10), pages 1143-1160, October.
    12. Dimitris Bertsimas & Ryan Cory-Wright, 2022. "A Scalable Algorithm for Sparse Portfolio Selection," INFORMS Journal on Computing, INFORMS, vol. 34(3), pages 1489-1511, May.
    13. Ruili Sun & Tiefeng Ma & Shuangzhe Liu, 2019. "Portfolio selection based on semivariance and distance correlation under minimum variance framework," Statistica Neerlandica, Netherlands Society for Statistics and Operations Research, vol. 73(3), pages 373-394, August.
    14. Óskarsdóttir, María & Bravo, Cristián, 2021. "Multilayer network analysis for improved credit risk prediction," Omega, Elsevier, vol. 105(C).
    15. Pierre Bonami & Miguel A. Lejeune, 2009. "An Exact Solution Approach for Integer Constrained Portfolio Optimization Problems Under Stochastic Constraints," Post-Print hal-00421756, HAL.
    16. Victor DeMiguel & Lorenzo Garlappi & Francisco J. Nogales & Raman Uppal, 2009. "A Generalized Approach to Portfolio Optimization: Improving Performance by Constraining Portfolio Norms," Management Science, INFORMS, vol. 55(5), pages 798-812, May.
    17. Wei-han Liu, 2017. "Optimal computing budget allocation to the differential evolution algorithm for large-scale portfolio optimization," Journal of Simulation, Taylor & Francis Journals, vol. 11(4), pages 380-390, November.
    18. Massimo Guidolin & Federica Ria, 2011. "Regime shifts in mean-variance efficient frontiers: Some international evidence," Journal of Asset Management, Palgrave Macmillan, vol. 12(5), pages 322-349, November.
    19. Gah-Yi Ban & Noureddine El Karoui & Andrew E. B. Lim, 2018. "Machine Learning and Portfolio Optimization," Management Science, INFORMS, vol. 64(3), pages 1136-1154, March.
    20. Cho, Younghwan & Song, Jae Wook, 2023. "Hierarchical risk parity using security selection based on peripheral assets of correlation-based minimum spanning trees," Finance Research Letters, Elsevier, vol. 53(C).
    21. Zhi-Long Dong & Fengmin Xu & Yu-Hong Dai, 2020. "Fast algorithms for sparse portfolio selection considering industries and investment styles," Journal of Global Optimization, Springer, vol. 78(4), pages 763-789, December.
    22. Andrew W. Lo, 2002. "The Statistics of Sharpe Ratios," Financial Analysts Journal, Taylor & Francis Journals, vol. 58(4), pages 36-52, July.
    23. Giovanni Petrella, 2005. "Are Euro Area Small Cap Stocks an Asset Class? Evidence from Mean‐Variance Spanning Tests," European Financial Management, European Financial Management Association, vol. 11(2), pages 229-253, March.
    24. Andrew F. Siegel & Artemiza Woodgate, 2007. "Performance of Portfolios Optimized with Estimation Error," Management Science, INFORMS, vol. 53(6), pages 1005-1015, June.
    Full references (including those not matched with items on IDEAS)

    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. Sven Husmann & Antoniya Shivarova & Rick Steinert, 2020. "Company classification using machine learning," Papers 2004.01496, arXiv.org, revised May 2020.
    2. Jacobs, Heiko & Müller, Sebastian & Weber, Martin, 2014. "How should individual investors diversify? An empirical evaluation of alternative asset allocation policies," Journal of Financial Markets, Elsevier, vol. 19(C), pages 62-85.
    3. Panos Xidonas & Christis Hassapis & George Mavrotas & Christos Staikouras & Constantin Zopounidis, 2018. "Multiobjective portfolio optimization: bridging mathematical theory with asset management practice," Annals of Operations Research, Springer, vol. 267(1), pages 585-606, August.
    4. Bonaccolto, Giovanni & Caporin, Massimiliano & Maillet, Bertrand B., 2022. "Dynamic large financial networks via conditional expected shortfalls," European Journal of Operational Research, Elsevier, vol. 298(1), pages 322-336.
    5. Ran Ji & Miguel A. Lejeune & Srinivas Y. Prasad, 2017. "Properties, formulations, and algorithms for portfolio optimization using Mean-Gini criteria," Annals of Operations Research, Springer, vol. 248(1), pages 305-343, January.
    6. Fan, Jianqing & Liao, Yuan & Shi, Xiaofeng, 2015. "Risks of large portfolios," Journal of Econometrics, Elsevier, vol. 186(2), pages 367-387.
    7. Seyoung Park & Eun Ryung Lee & Sungchul Lee & Geonwoo Kim, 2019. "Dantzig Type Optimization Method with Applications to Portfolio Selection," Sustainability, MDPI, vol. 11(11), pages 1-32, June.
    8. Peralta, Gustavo & Zareei, Abalfazl, 2016. "A network approach to portfolio selection," Journal of Empirical Finance, Elsevier, vol. 38(PA), pages 157-180.
    9. Füss, Roland & Miebs, Felix & Trübenbach, Fabian, 2014. "A jackknife-type estimator for portfolio revision," Journal of Banking & Finance, Elsevier, vol. 43(C), pages 14-28.
    10. Tae-Hwy Lee & Ekaterina Seregina, 2024. "Optimal Portfolio Using Factor Graphical Lasso," Journal of Financial Econometrics, Oxford University Press, vol. 22(3), pages 670-695.
    11. Ye, Liping & Geng, Jiang-Bo, 2021. "Measuring the connectedness of global health sector stock markets," Pacific-Basin Finance Journal, Elsevier, vol. 68(C).
    12. Wang, Gang-Jin & Chen, Yang-Yang & Si, Hui-Bin & Xie, Chi & Chevallier, Julien, 2021. "Multilayer information spillover networks analysis of China’s financial institutions based on variance decompositions," International Review of Economics & Finance, Elsevier, vol. 73(C), pages 325-347.
    13. Costantini, Mauro & Maaitah, Ahmad & Mishra, Tapas & Sousa, Ricardo M., 2023. "Bitcoin market networks and cyberattacks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 630(C).
    14. Gang-Jin Wang & Chi Xie & Kaijian He & H. Eugene Stanley, 2017. "Extreme risk spillover network: application to financial institutions," Quantitative Finance, Taylor & Francis Journals, vol. 17(9), pages 1417-1433, September.
    15. Weidong Lin & Jose Olmo & Abderrahim Taamouti, 2022. "Portfolio Selection Under Systemic Risk," Working Papers 202208, University of Liverpool, Department of Economics.
    16. Sun, Chuting & Wu, Qi & Yan, Xing, 2024. "Dynamic CVaR portfolio construction with attention-powered generative factor learning," Journal of Economic Dynamics and Control, Elsevier, vol. 160(C).
    17. Dimitris Bertsimas & Ryan Cory-Wright, 2022. "A Scalable Algorithm for Sparse Portfolio Selection," INFORMS Journal on Computing, INFORMS, vol. 34(3), pages 1489-1511, May.
    18. Lioui, Abraham & Tarelli, Andrea, 2022. "Chasing the ESG factor," Journal of Banking & Finance, Elsevier, vol. 139(C).
    19. Matteo Barigozzi & Christian Brownlees, 2019. "NETS: Network estimation for time series," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 34(3), pages 347-364, April.
    20. Gianluca De Nard & Olivier Ledoit & Michael Wolf, 2018. "Factor models for portfolio selection in large dimensions: the good, the better and the ugly," ECON - Working Papers 290, Department of Economics - University of Zurich, revised Dec 2018.

    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:2407.15532. 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.