IDEAS home Printed from https://ideas.repec.org/p/cir/cirwor/2002s-49.html

Cost Functions and Model Combination for VaR-based Asset Allocation using Neural Networks

Author

Listed:
  • Yoshua Bengio
  • Nicolas Chapados

Abstract

We introduce an asset-allocation framework based on the active control of the value-at- risk of the portfolio. Within this framework, we compare two paradigms for making the allocation using neural networks. The first one uses the network to make a forecast of asset behavior, in conjunction with a traditional mean-variance allocator for constructing the portfolio. The second paradigm uses the network to directly make the portfolio allocation decisions. We consider a method for performing soft input variable selection, and show its considerable utility. We use model combination (committee) methods to systematize the choice of hyperparemeters during training. We show that committees using both paradigms are significantly outperforming the benchmark market performance. Nous introduisons un cadre d'allocation d'actifs basé sur le contrôle actif de la valeur à risque d'un portefeuille. À l'intérieur de ce cadre, nous comparons deux paradigmes pour faire cette allocation à l'aide de réseaux de neurones. Le premier paradigme utilise le réseau de neurones pour faire une prédiction sur le comportement de l'actif, en conjonction avec un allocateur traditionnel de moyenne-variance pour la construction du portefeuille. Le deuxième paradigme utilise le réseau pour faire directement les décisions d'allocation du portefeuille. Nous considérons une méthode qui accomplit une sélection de variable douce sur les entrées, et nous montrons sa très grande utilité. Nous utilisons également des méthodes de combinaison de modèles (comité) pour choisir systématiquement les hyper-paramètres pendant l'entraînement. Finalement, nous montrons que les comités utilisant les deux paradigmes surpassent de façon significative les performances d'un banc d'essai du marché.

Suggested Citation

  • Yoshua Bengio & Nicolas Chapados, 2002. "Cost Functions and Model Combination for VaR-based Asset Allocation using Neural Networks," CIRANO Working Papers 2002s-49, CIRANO.
  • Handle: RePEc:cir:cirwor:2002s-49
    as

    Download full text from publisher

    File URL: https://cirano.qc.ca/files/publications/2002s-49.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Halbert White, 2000. "A Reality Check for Data Snooping," Econometrica, Econometric Society, vol. 68(5), pages 1097-1126, September.
    2. John Moody & Lizhong Wu, "undated". "Optimization of Trading Systems and Portfolios," Computing in Economics and Finance 1997 55, Society for Computational Economics.
    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. Lee, Tae-Hwy & Yang, Weiping, 2014. "Granger-causality in quantiles between financial markets: Using copula approach," International Review of Financial Analysis, Elsevier, vol. 33(C), pages 70-78.
    2. Alexandre Belloni & Victor Chernozhukov & Denis Chetverikov & Christian Hansen & Kengo Kato, 2018. "High-dimensional econometrics and regularized GMM," CeMMAP working papers CWP35/18, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    3. Marcelo Fernandes & Breno Neri, 2010. "Nonparametric Entropy-Based Tests of Independence Between Stochastic Processes," Econometric Reviews, Taylor & Francis Journals, vol. 29(3), pages 276-306.
    4. Adriano Koshiyama & Sebastian Flennerhag & Stefano B. Blumberg & Nick Firoozye & Philip Treleaven, 2020. "QuantNet: Transferring Learning Across Systematic Trading Strategies," Papers 2004.03445, arXiv.org, revised Jun 2020.
    5. Darvas, Zsolt, 2009. "Leveraged carry trade portfolios," Journal of Banking & Finance, Elsevier, vol. 33(5), pages 944-957, May.
    6. David E. Rapach & Jack K. Strauss, 2008. "Structural breaks and GARCH models of exchange rate volatility," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 23(1), pages 65-90.
    7. Arvanitis, Stelios & Post, Thierry & Potì, Valerio & Karabati, Selcuk, 2021. "Nonparametric tests for Optimal Predictive Ability," International Journal of Forecasting, Elsevier, vol. 37(2), pages 881-898.
    8. Lux, Thomas & Segnon, Mawuli & Gupta, Rangan, 2016. "Forecasting crude oil price volatility and value-at-risk: Evidence from historical and recent data," Energy Economics, Elsevier, vol. 56(C), pages 117-133.
    9. Christina Ziegler, 2009. "Testing Predicitive Ability of Business Cycle Indicators for the Euro Area," ifo Working Paper Series 69, ifo Institute - Leibniz Institute for Economic Research at the University of Munich.
    10. Valentina Corradi & Norman Swanson, 2013. "A Survey of Recent Advances in Forecast Accuracy Comparison Testing, with an Extension to Stochastic Dominance," Departmental Working Papers 201309, Rutgers University, Department of Economics.
    11. Bajgrowicz, Pierre & Scaillet, Olivier, 2012. "Technical trading revisited: False discoveries, persistence tests, and transaction costs," Journal of Financial Economics, Elsevier, vol. 106(3), pages 473-491.
    12. Zhao, Yang & Li, Jianping & Yu, Lean, 2017. "A deep learning ensemble approach for crude oil price forecasting," Energy Economics, Elsevier, vol. 66(C), pages 9-16.
    13. Sager, Michael & Taylor, Mark P., 2014. "Generating currency trading rules from the term structure of forward foreign exchange premia," Journal of International Money and Finance, Elsevier, vol. 44(C), pages 230-250.
    14. Anthony S. Tay, 2006. "Mixing Frequencies : Stock Returns as a Predictor of Real Output Growth," Macroeconomics Working Papers 22480, East Asian Bureau of Economic Research.
    15. Marco Rocco, 2011. "Extreme value theory for finance: a survey," Questioni di Economia e Finanza (Occasional Papers) 99, Bank of Italy, Economic Research and International Relations Area.
    16. Wen Cheong Chin & Min Cherng Lee, 2018. "S&P500 volatility analysis using high-frequency multipower variation volatility proxies," Empirical Economics, Springer, vol. 54(3), pages 1297-1318, May.
    17. Chuliá, Helena & Guillén, Montserrat & Uribe, Jorge M., 2017. "Spillovers from the United States to Latin American and G7 stock markets: A VAR quantile analysis," Emerging Markets Review, Elsevier, vol. 31(C), pages 32-46.
    18. Corradi, Valentina & Swanson, Norman R., 2004. "A test for the distributional comparison of simulated and historical data," Economics Letters, Elsevier, vol. 85(2), pages 185-193, November.
    19. Todd E. Clark & Michael W. McCracken, 2010. "Averaging forecasts from VARs with uncertain instabilities," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 25(1), pages 5-29, January.
    20. Chiang, Mi-Hsiu & Chiu, Hsin-Yu & Kuo, Wei-Yu, 2021. "Predictive ability of similarity-based futures trading strategies," Pacific-Basin Finance Journal, Elsevier, vol. 68(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;
    ;
    ;
    ;
    ;

    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:cir:cirwor:2002s-49. 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: Webmaster (email available below). General contact details of provider: https://edirc.repec.org/data/ciranca.html .

    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.