Forecasting the term structure of crude oil futures prices with neural networks

0453168 - ÚTIA 2017 RIV GB eng J - Journal Article
Baruník, Jozef - Malinská, B.
Forecasting the term structure of crude oil futures prices with neural networks.
Applied Energy. Roč. 164, č. 1 (2016), s. 366-379. ISSN 0306-2619. E-ISSN 1872-9118
R&D Projects: GA ČR(CZ) GBP402/12/G097
Institutional support: RVO:67985556
Keywords : Term structure * Nelson–Siegel model * Dynamic neural networks * Crude oil futures
Subject RIV: AH - Economics
Impact factor: 7.182, year: 2016
http://library.utia.cas.cz/separaty/2016/E/barunik-0453168.pdf

The paper contributes to the limited literature modelling the term structure of crude oil markets. We explain the term structure of crude oil prices using the dynamic Nelson–Siegel model and propose to forecast oil prices using a 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 a 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.
Permanent Link: http://hdl.handle.net/11104/0260446