The role of supervised learning in the decision process to fair trade US municipal debt

Abstract

Determining a fair price and an appropriate timescale to trade municipal debt is a complex decision. This research uses data informatics to explore transaction characteristics and trading activity of investment grade US municipal bonds. Using the relatively recent data stream distributed by the Municipal Securities Rulemaking Board, we provide an institutional summary of market participants and their trading behavior. Subsequently, we focus on a sample of AAA bonds to derive a new methodology to estimate a trade-weighted benchmark municipal yield curve. The methodology integrates the study of ridge regression, artificial neural networks, and support vector regression. We find an enhanced radial basis function artificial neural network outperforms alternate methods used to estimate municipal term structure. This result forms the foundation for establishing a decision theory on optimal municipal bond trading. Using multivariate modeling of a liquidity domain measured across three dependent variables, we investigate the proposed decision theory by estimating weekly production-theoretic bond liquidity returns to scale. Across the three liquidity measures and for almost all weeks investigated, bond trading liquidity is elastic with respect to the modeled factors. This finding leads us to conclude that an optimal trading policy for municipal debt can be implemented on a weekly timescale using the elasticity estimates of bond price, trade size, risk, days-to-maturity, and the macroeconomic influences of labor in the workforce and building activity.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Notes

  1. 1.

    Creal and Wu (2014) provide an alternative research strain based on affine models to demonstrate how spanned stochastic volatility captures either the cross section of yields or the fitted volatility.

  2. 2.

    For a complete listing, see: http://bit.ly/2eZvyY5.

  3. 3.

    All term structure curves are available at: http://bit.ly/2eZvyY5.

  4. 4.

    B-spline or basis spline is a spline function that has minimal support with respect to a given degree, smoothness, and domain partition (Wikipedia). It is provided here only as a base comparative method.

References

  1. Aguilar LA (2015) Statement on making the municipal securities market more transparent, liquid, and fair US securities and exchange commission, http://bit.ly/2uOsamN

  2. Almeida C, Ardison K, Kubudi D, Simonsen A, Vicente J (2017) Forecasting bond yields with segmented term structure models. J Financ Econ 16(1):1–33

    Google Scholar 

  3. Amihud Y (2002) Illiquidity and stock returns: cross-section and time-series effects. J Financ Mark 5:31–56

    Article  Google Scholar 

  4. Ang A, Piazzesi M (2003) A no-arbitrage vector autoregression of term structure dynamics with macroeconomic and latent variables. J Mon Econ 50:745–787

    Article  Google Scholar 

  5. Annaert J, Claes AGP, De Ceuster MJK, Zhang H (2010) Estimating the yield curve using the nelson-siegel model. European Financial Management Association, Aarhus

    Google Scholar 

  6. Bao J, Pan J, Wang J (2011) The illiquidity of corporate bonds. J Financ 66:911–946

    Article  Google Scholar 

  7. Bowsher CG, Meeks R (2013) Stationarity and the term structure of interest rates: a characterization of stationary and unit root yield curves

  8. Cobb CW, Douglas PH (1928) A theory of production. Am Econ Rev 18:139–165

    Google Scholar 

  9. Cox JC, Ingersoll JE, Ross SA (1985) A theory of the term structure of interest rates. Econometrica 53:385–408

    Article  Google Scholar 

  10. Creal DD, Wu JC (2015) Estimation of affine term structure models with spanned or unspanned stochastic volatility. J Econ 85(1):60–81

    Article  Google Scholar 

  11. Dai Q, Singleton KJ (2000) Specification analysis of affine term structure models. J Financ 55:1943–1978

    Article  Google Scholar 

  12. Dai Q, Singleton KJ, Yang W (2007) Regime shifts in a dynamic term structure model of U.S treasury bond yields. Rev Financ Stud Soc Financ Stud 20:1669–1706

    Article  Google Scholar 

  13. Daniels K, Ejara DD (2009) Impact of information asymmetry on municipal bond yields: an empirical analysis. Am J Econ Bus Admin 1:11–20

    Google Scholar 

  14. Dash GH Jr, Kajiji N (2003) New evidence on the predictability of South African Fx volatility in heterogenous bilateral markets. Afr Financ J 5:1–15

    Google Scholar 

  15. Dash GH Jr, Kajiji N (2008) Engineering a generalized neural network mapping of volatility spillovers in european government bond markets. In: Zopounidis C, Doumpos M, Pardalos PM (eds) Handbook of financial engineering, optimization and its applications, vol 18. Springer, Berlin

    Google Scholar 

  16. Dash Jr. GH, Kajiji N Modeling FX (2002) Volatility: a comparative analysis of the rbf neural network topology. In: 9th international conference on forecasting financial markets, London, England

  17. Dash Jr. GH, Hanumara C, Kajiji N (2003) Neural network architectures for modeling fx futures options volatility. In: Annual Meetings of the Northeast Decision Sciences Institute, Providence, Rhode Island

  18. De Pooter M (2007) Examining the Nelson-Siegel class of term structure models. Tinbergen Institute, Amsterdam

    Google Scholar 

  19. De Pooter M, Ravazzolo F, van Dijk D (2010) Term structure forecasting using macro factors and forecast combination. Board of governors of the federal reserve system, Discussion paper 993

  20. Diebold FX, Li C (2006) Forecasting the term structure of government bond yields. J Econ 130:337–364

    Article  Google Scholar 

  21. Diebold FX, Rudebusch GD, Boragan AS (2006) The macroeconomy and the yield curve: a dynamic latent factor approach. J Econ 131:309–338

    Article  Google Scholar 

  22. Drucker H, Burges CJ, Kaufam L, Smola A, Vapnik V (1996) Support vector regression machines. In: NIPS’96 proceedings of the 9th international conference on neural information processing systems, Denver, CO, 1996. MIT Press, Cambridge, MA

  23. Edwards AK, Harris LE, Piwowar MS (2007) Corporate bond market transaction costs and transparency. J Financ 62:1421–1451

    Article  Google Scholar 

  24. Fabozzi FJ, Martellini L, Priaulet P (2005) Predictability in the Shape of the Term Structure of Interest Rates. J Fixed Income 15:40–53

    Article  Google Scholar 

  25. Feldhütter P (2012) The same bond at different prices: identifying search frictions and selling pressures. Rev Financ Stud 25:1155–1206

    Article  Google Scholar 

  26. Geldera LV, Dasb P, Janssena H, Roelsa S (2014) Comparative study of metamodelling techniques in building energy simulation: guidelines for practitioners. Simul Model Pract Theory 49:245–257

    Article  Google Scholar 

  27. Goldstein M, Hotchkiss ES (2015) Dealer behavior in highly illiquid risky assets. Queens University, Belfast

    Google Scholar 

  28. Gonzalez-Rozada M, Sola M, Hevia C, Spagnolo F (2012) Estimating and forecasting the yield curve using a markov switching dynamic nelson and siegel model. Universidad Torcuato Di Tella, Buenos Aires

    Google Scholar 

  29. Harris LE, Piwowar MS (2006) Secondary trading costs in the municipal bond market. J Financ 61:1361–1397

    Article  Google Scholar 

  30. Iglewicz B, Hoaglin D (1993) How to detect and handle outliers. In: Mykytka EF (ed) The ASQC basic reference in quality control: statistical techniques, vol 16. American Society for Quality Control Statistics Division, Milwaukee

    Google Scholar 

  31. Juillard M, Villemot S (2011) Multi-country real business cycle models: accuracy tests and test bench. J Econ Dyn Control 35:178–185

    Article  Google Scholar 

  32. Kajiji N (2001) Adaptation of alternative closed form regularization parameters with prior information to the radial basis function neural network for high frequency financial time series. University of Rhode Island

  33. Kajiji N, Dash GH Jr (2013) On the behavioral specification and multivariate neural network estimation of cognitive scale economies. J Appl Operat Res 5:30–40

    Google Scholar 

  34. Kalotay AJ, Dorigan MP (2009) What makes the municipal yield curve rise? J Fixed Income 18(3):65

    Article  Google Scholar 

  35. Lin H, Liu S, Wang J, Wu C (2010) Liquidity and the pricing of municipal bonds. In: Proceedings of the 2010 China international conference in finance, Beijing, China

  36. Mizrach B (2015) Analysis of corporate bond liquidity. FINRA Office of the Chief Economist. http://bit.ly/2wbO9Dw

  37. Moench E (2008) Forecasting the yield curve in a data-rich environment: a no-arbitrage factor-augmented var approach. J Econ 146:26–43

    Article  Google Scholar 

  38. Moraux F, Pakulyak O (2016) Which term structure of interest rates model performs the best to price the government bonds in euro area? Paper presented at the forecasting financial markets, Hannover, Germany

  39. Nelson CR, Siegel A (1987) Parismoious modeling of yield curves. J Bus 60:473–489

    Article  Google Scholar 

  40. Olej V, Hájek P (2009) Municipal creditworthiness modelling by radial basis function neural networks and sensitive analysis of their input parameters. In: Alippi C, Polycarpou M, Panayiotou C, Ellinas G (eds) Artificial neural networks—ICANN 2009. Lecture notes in computer science. Springer, Berlin, pp 505–514

    Google Scholar 

  41. Piazzesi M (2010) Affine term structure models. In: Ait-Sahalia Y, Hansen L (eds) Handbook of financial econometrics: tools and techniques, vol 1. Handbooks in Finance, Elesvier

    Google Scholar 

  42. Ratrout NT, Gazder U (2014) Factors affecting performance of parametric and non-parametric models for daily traffic forecasting. In: 5th international conference on ambient systems, networks and technologies, Procedia Computer Science 32:285-292

  43. Steenbarger BN (2003) The psychology of trading: tools and techniques for minding the markets. Wiley, Hoboken

    Google Scholar 

  44. Vapnik V (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  45. Vasicek O (1977) An equilibrium characterization of the term structure. J Financ Econ 5:177–188

    Article  Google Scholar 

  46. Xiang J, Zhu X (2013) A regime-switching Nelson-Siegel term structure model and interest rate forecasts. J Financ Econ 11:522–555

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Gordon H. Dash.

Additional information

Submitted for publication consideration in the Feature Issue on “Financial Decision Support”, Euro Journal on Decision Processes, 30 July 2017.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 914 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Dash, G.H., Kajiji, N. & Vonella, D. The role of supervised learning in the decision process to fair trade US municipal debt. EURO J Decis Process 6, 139–168 (2018). https://doi.org/10.1007/s40070-018-0079-2

Download citation

Keywords

  • Decision theory
  • Municipal bonds
  • Supervised learning
  • Production theory

JEL Classification

  • C15
  • C45
  • C55
  • C58