Forecasting the Term Structure of Crude Oil Futures Prices with Neural Networks

The paper contributes to the rare literature modeling term structure of crude oil markets. We explain term structure of crude oil prices using dynamic Nelson-Siegel model, and propose to forecast them with the generalized regression framework based on neural networks. The newly proposed framework is empirically tested on 24 years of crude oil futures prices covering several important recessions and crisis periods. We find 1-month, 3-month, 6-month and 12-month-ahead forecasts obtained from focused time-delay neural network to be significantly more accurate than forecasts from other benchmark models. The proposed forecasting strategy produces the lowest errors across all times to maturity.

[1]  N. Nomikos,et al.  Petroleum Term Structure Dynamics and the Role of Regimes , 2015 .

[2]  H. Hotelling.  The economics of exhaustible resources , 1931, Journal of Political Economy.

[3]  H. An,et al.  Selecting dynamic moving average trading rules in the crude oil futures market using a genetic approach , 2016 .

[4]  Jozef Baruník,et al.  Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility , 2014 .

[5]  Florentina Paraschiv,et al.  Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks , 2016 .

[6]  N. Nomikos,et al.  Forecasting petroleum futures markets volatility: The role of regimes and market conditions , 2011 .

[7]  C. Aloui,et al.  Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling , 2012 .

[8]  Haruna Chiroma,et al.  Evolutionary Neural Network model for West Texas Intermediate crude oil price prediction , 2015 .

[9]  D. Duffie,et al.  A Yield-factor Model of Interest Rates , 1996 .

[10]  D. Lautier.  Term Structure Models of Commodity Prices , 2005 .

[11]  K. Lai,et al.  Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm , 2008 .

[12]  Eduardo S. Schwartz,et al.  Evaluating Natural Resource Investments , 1985 .

[13]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[14]  Glyn A. Holton.  Value at Risk: Theory and Practice , 2003 .

[15]  R. Bliss.  Testing Term Structure Estimation Methods , 1996 .

[16]  Garrison W. Cottrell,et al.  Time-delay neural networks: representation and induction of finite-state machines , 1997, IEEE Trans. Neural Networks.

[17]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[18]  Dick J. C. van Dijk,et al.  Common Factors in Commodity Futures Curves , 2015 .

[19]  The Term Structures of Oil Futures Prices , 1991 .

[20]  Daniel Vela.  Forecasting Latin-American yield curves: An artificial neural network approach , 2013 .

[21]  Yue-Jun Zhang,et al.  Speculative trading and WTI crude oil futures price movement: An empirical analysis , 2013 .

[22]  J. Steeley.  Testing term structure estimation methods: evidence from the UK STRIPs market , 2008 .

[23]  Bao-Jun Tang,et al.  The efficiency analysis of the European CO2 futures market , 2013 .

[24]  Joarder Kamruzzaman,et al.  Artificial Neural Networks: Applications in Finance and Manufacturing , 2006 .

[25]  Eduardo S. Schwartz.  The stochastic behavior of commodity prices: Implications for valuation and hedging , 1997 .

[26]  R. Litzenberger,et al.  Backwardation in Oil Futures Markets: Theory and Empirical Evidence , 1995 .

[27]  Zhongyi Hu,et al.  Beyond One-Step-Ahead Forecasting: Evaluation of Alternative Multi-Step-Ahead Forecasting Models for Crude Oil Prices , 2013, ArXiv.

[28]  Joseph G. Haubrich,et al.  Oil prices: backward to the future? , 2004 .

[29]  Lutz Kilian,et al.  Do High-Frequency Financial Data Help Forecast Oil Prices? The Midas Touch at Work , 2013 .

[30]  L. Kilian,et al.  The Role of Speculation in Oil Markets: What Have We Learned So Far? , 2012 .

[31]  James D. Hamilton.  Causes and Consequences of the Oil Shock of 2007–08 , 2009 .

[32]  A. Siegel,et al.  Parsimonious modeling of yield curves , 1987 .

[33]  Yudong Wang,et al.  Forecasting energy market volatility using GARCH models: Can multivariate models beat univariate models? , 2012 .

[34]  Haizhong An,et al.  Research on patterns in the fluctuation of the co-movement between crude oil futures and spot prices: A complex network approach , 2014 .

[35]  R. Sarker,et al.  Artificial Neural Networks in Finance and Manufacturing , 2006 .

[36]  Yi-Ming Wei,et al.  A generalized pattern matching approach for multi-step prediction of crude oil price , 2008 .

[37]  Heping Pan,et al.  Daily prediction of short-term trends of crude oil prices using neural networks exploiting multimarket dynamics , 2009, Frontiers of Computer Science in China.

[38]  F. Diebold,et al.  Forecasting the Term Structure of Government Bond Yields , 2002 .

[39]  Saeid R. Dindarloo,et al.  Prediction of fuel consumption of mining dump trucks: A neural networks approach , 2015 .

[40]  T. Brailsford,et al.  An evaluation of volatility forecasting techniques , 1996 .

[41]  Lutz Kilian,et al.  The Role of Inventories and Speculative Trading in the Global Market for Crude Oil , 2010 .

[42]  P. Hansen.  A Test for Superior Predictive Ability , 2005 .

[43]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[44]  A. Kialashaki,et al.  Modeling of the energy demand of the residential sector in the United States using regression models and artificial neural networks , 2013 .

[45]  Xinwei Zheng,et al.  Gold and oil futures markets: Are markets efficient? , 2010 .

[46]  H. White,et al.  A Reality Check for Data Snooping , 2000 .

[47]  Investigating price clustering in the oil futures market , 2011 .

[48]  Patrick S. Hagan,et al.  Interpolation Methods for Curve Construction , 2006 .

[49]  Periklis Gogas,et al.  Forecasting energy markets using support vector machines , 2014 .

[50]  Abdullah Almansour,et al.  Convenience yield in commodity price modeling: A regime switching approach , 2016 .

[51]  Niels S. Grønborg,et al.  Analyzing Oil Futures with a Dynamic Nelson‐Siegel Model , 2016 .

[52]  Gonzalo Cortazar,et al.  Implementing a stochastic model for oil futures prices , 2003 .

[53]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[54]  Frieder Mokinski,et al.  The impact of fundamental and financial traders on the term structure of oil , 2015 .

[55]  Bahattin Buyuksahin,et al.  Do Speculators Drive Crude Oil Futures Prices? , 2011 .