IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2005.02217.html
   My bibliography  Save this paper

Long short-term memory networks and laglasso for bond yield forecasting: Peeping inside the black box

Author

Listed:
  • Manuel Nunes
  • Enrico Gerding
  • Frank McGroarty
  • Mahesan Niranjan

Abstract

Modern decision-making in fixed income asset management benefits from intelligent systems, which involve the use of state-of-the-art machine learning models and appropriate methodologies. We conduct the first study of bond yield forecasting using long short-term memory (LSTM) networks, validating its potential and identifying its memory advantage. Specifically, we model the 10-year bond yield using univariate LSTMs with three input sequences and five forecasting horizons. We compare those with multilayer perceptrons (MLP), univariate and with the most relevant features. To demystify the notion of black box associated with LSTMs, we conduct the first internal study of the model. To this end, we calculate the LSTM signals through time, at selected locations in the memory cell, using sequence-to-sequence architectures, uni and multivariate. We then proceed to explain the states' signals using exogenous information, for what we develop the LSTM-LagLasso methodology. The results show that the univariate LSTM model with additional memory is capable of achieving similar results as the multivariate MLP using macroeconomic and market information. Furthermore, shorter forecasting horizons require smaller input sequences and vice-versa. The most remarkable property found consistently in the LSTM signals, is the activation/deactivation of units through time, and the specialisation of units by yield range or feature. Those signals are complex but can be explained by exogenous variables. Additionally, some of the relevant features identified via LSTM-LagLasso are not commonly used in forecasting models. In conclusion, our work validates the potential of LSTMs and methodologies for bonds, providing additional tools for financial practitioners.

Suggested Citation

  • Manuel Nunes & Enrico Gerding & Frank McGroarty & Mahesan Niranjan, 2020. "Long short-term memory networks and laglasso for bond yield forecasting: Peeping inside the black box," Papers 2005.02217, arXiv.org.
  • Handle: RePEc:arx:papers:2005.02217
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2005.02217
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Luis Montesdeoca & Mahesan Niranjan, 2020. "On Comparing the Influences of Exogenous Information on Bitcoin Prices and Stock Index Values," Springer Proceedings in Business and Economics, in: Panos Pardalos & Ilias Kotsireas & Yike Guo & William Knottenbelt (ed.), Mathematical Research for Blockchain Economy, pages 93-100, Springer.
    2. Kanevski, M. & Maignan, M. & Pozdnoukhov, A. & Timonin, V., 2008. "Interest rates mapping," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 387(15), pages 3897-3903.
    3. Jing Yang & Nikola Gradojevic, 2006. "Non-linear, non-parametric, non-fundamental exchange rate forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 25(4), pages 227-245.
    4. Tristan Fletcher & John Shawe-Taylor, 2013. "Multiple Kernel Learning with Fisher Kernels for High Frequency Currency Prediction," Computational Economics, Springer;Society for Computational Economics, vol. 42(2), pages 217-240, August.
    5. Diebold, Francis X. & Li, Canlin, 2006. "Forecasting the term structure of government bond yields," Journal of Econometrics, Elsevier, vol. 130(2), pages 337-364, February.
    6. Sermpinis, Georgios & Theofilatos, Konstantinos & Karathanasopoulos, Andreas & Georgopoulos, Efstratios F. & Dunis, Christian, 2013. "Forecasting foreign exchange rates with adaptive neural networks using radial-basis functions and Particle Swarm Optimization," European Journal of Operational Research, Elsevier, vol. 225(3), pages 528-540.
    7. Marco Castellani & Emanuel Santos, 2006. "Forecasting Long-Term Government Bond Yields: An Application of Statistical and AI Models," Working Papers Department of Economics 2006/04, ISEG - Lisbon School of Economics and Management, Department of Economics, Universidade de Lisboa.
    8. Christian L. Dunis & Vincent Morrison, 2007. "The Economic Value of Advanced Time Series Methods for Modelling and Trading 10-year Government Bonds," The European Journal of Finance, Taylor & Francis Journals, vol. 13(4), pages 333-352.
    9. Jingyuan Wang & Yang Zhang & Ke Tang & Junjie Wu & Zhang Xiong, 2019. "AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks," Papers 1908.02646, arXiv.org.
    10. Antonios Antoniou & Emilios C. C Galariotis & Spyros I. Spyrou, 2003. "Profits From Buying Losers And Selling Winners In The London Stock Exchange," Post-Print hal-01096057, HAL.
    11. Aditya R. Khanal & Ashok K. Mishra, 2014. "Is the 'buying winners and selling losers' trading strategy profitable in the New Economy?," Applied Economics Letters, Taylor & Francis Journals, vol. 21(15), pages 1090-1093, October.
    12. Nelson, Charles R & Siegel, Andrew F, 1987. "Parsimonious Modeling of Yield Curves," The Journal of Business, University of Chicago Press, vol. 60(4), pages 473-489, October.
    13. Wei Huang & Kin Keung Lai & Yoshiteru Nakamori & Shouyang Wang & Lean Yu, 2007. "Neural Networks In Finance And Economics Forecasting," International Journal of Information Technology & Decision Making (IJITDM), World Scientific Publishing Co. Pte. Ltd., vol. 6(01), pages 113-140.
    14. Neil Kellard & Denise Osborn & Jerry Coakley & Imanol Arrieta-ibarra & Ignacio N. Lobato, 2015. "Testing for Predictability in Financial Returns Using Statistical Learning Procedures," Journal of Time Series Analysis, Wiley Blackwell, vol. 36(5), pages 672-686, September.
    15. Jegadeesh, Narasimhan & Titman, Sheridan, 1993. "Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency," Journal of Finance, American Finance Association, vol. 48(1), pages 65-91, March.
    16. Fischer, Thomas & Krauss, Christopher, 2018. "Deep learning with long short-term memory networks for financial market predictions," European Journal of Operational Research, Elsevier, vol. 270(2), pages 654-669.
    17. Ruoxuan Xiong & Eric P. Nichols & Yuan Shen, 2015. "Deep Learning Stock Volatility with Google Domestic Trends," Papers 1512.04916, arXiv.org, revised Feb 2016.
    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. Wei Pan & Jide Li & Xiaoqiang Li, 2020. "Portfolio Learning Based on Deep Learning," Future Internet, MDPI, vol. 12(11), pages 1-13, November.
    2. Flori, Andrea & Regoli, Daniele, 2021. "Revealing Pairs-trading opportunities with long short-term memory networks," European Journal of Operational Research, Elsevier, vol. 295(2), pages 772-791.
    3. Rubesam, Alexandre, 2022. "Machine learning portfolios with equal risk contributions: Evidence from the Brazilian market," Emerging Markets Review, Elsevier, vol. 51(PB).
    4. Sergio Consoli & Luca Tiozzo Pezzoli & Elisa Tosetti, 2022. "Neural forecasting of the Italian sovereign bond market with economic news," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 185(S2), pages 197-224, December.
    5. Sudarshan Kumar & Sobhesh Kumar Agarwalla & Jayanth R. Varma & Vineet Virmani, 2023. "Harvesting the volatility smile in a large emerging market: A Dynamic Nelson–Siegel approach," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 43(11), pages 1615-1644, November.
    6. Kessler, Stephan & Scherer, Bernd, 2009. "Varying risk premia in international bond markets," Journal of Banking & Finance, Elsevier, vol. 33(8), pages 1361-1375, August.
    7. Söhnke M. Bartram & Jürgen Branke & Mehrshad Motahari, 2020. "Artificial intelligence in asset management," Working Papers 20202001, Cambridge Judge Business School, University of Cambridge.
    8. Gradojevic, Nikola & Kukolj, Dragan & Adcock, Robert & Djakovic, Vladimir, 2023. "Forecasting Bitcoin with technical analysis: A not-so-random forest?," International Journal of Forecasting, Elsevier, vol. 39(1), pages 1-17.
    9. Kearney, Fearghal & Shang, Han Lin & Sheenan, Lisa, 2019. "Implied volatility surface predictability: The case of commodity markets," Journal of Banking & Finance, Elsevier, vol. 108(C).
    10. Eric Hillebrand & Huiyu Huang & Tae-Hwy Lee & Canlin Li, 2018. "Using the Entire Yield Curve in Forecasting Output and Inflation," Econometrics, MDPI, vol. 6(3), pages 1-27, August.
    11. Matsumura, Marco & Moreira, Ajax & Vicente, José, 2011. "Forecasting the yield curve with linear factor models," International Review of Financial Analysis, Elsevier, vol. 20(5), pages 237-243.
    12. Wei Dai & Yuan An & Wen Long, 2021. "Price change prediction of ultra high frequency financial data based on temporal convolutional network," Papers 2107.00261, arXiv.org.
    13. Lily Y. Liu, 2017. "Estimating Loss Given Default from CDS under Weak Identification," Supervisory Research and Analysis Working Papers RPA 17-1, Federal Reserve Bank of Boston.
    14. Bowsher, Clive G. & Meeks, Roland, 2008. "The Dynamics of Economic Functions: Modeling and Forecasting the Yield Curve," Journal of the American Statistical Association, American Statistical Association, vol. 103(484), pages 1419-1437.
    15. Dick Dijk & Siem Jan Koopman & Michel Wel & Jonathan H. Wright, 2014. "Forecasting interest rates with shifting endpoints," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 29(5), pages 693-712, August.
    16. Gary S. Anderson & Alena Audzeyeva, 2019. "A Coherent Framework for Predicting Emerging Market Credit Spreads with Support Vector Regression," Finance and Economics Discussion Series 2019-074, Board of Governors of the Federal Reserve System (U.S.).
    17. Norman R. Swanson & Weiqi Xiong, 2018. "Big data analytics in economics: What have we learned so far, and where should we go from here?," Canadian Journal of Economics/Revue canadienne d'économique, John Wiley & Sons, vol. 51(3), pages 695-746, August.
    18. João Frois Caldeira & Rangan Gupta & Muhammad Tahir Suleman & Hudson S. Torrent, 2021. "Forecasting the Term Structure of Interest Rates of the BRICS: Evidence from a Nonparametric Functional Data Analysis," Emerging Markets Finance and Trade, Taylor & Francis Journals, vol. 57(15), pages 4312-4329, December.
    19. Hautsch, Nikolaus & Yang, Fuyu, 2012. "Bayesian inference in a Stochastic Volatility Nelson–Siegel model," Computational Statistics & Data Analysis, Elsevier, vol. 56(11), pages 3774-3792.
    20. Adam Traczyk, 2013. "Financial integration and the term structure of interest rates," Empirical Economics, Springer, vol. 45(3), pages 1267-1305, December.

    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:2005.02217. 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.