PMID- 32518424
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240328
IS  - 0040-1625 (Print)
IS  - 0040-1625 (Electronic)
IS  - 0040-1625 (Linking)
VI  - 158
DP  - 2020 Sep
TI  - A novel hybrid approach to forecast crude oil futures using intraday data.
PG  - 120126
LID - 10.1016/j.techfore.2020.120126 [doi]
AB  - Prediction of oil prices is an implausible task due to the multifaceted nature of 
      oil markets. This study presents two novel hybrid models to forecast WTI and 
      Brent crude oil prices using combinations of machine learning and nature inspired 
      algorithms. The first approach, MARSplines-IPSO-BPNN, Multivariate Adaptive 
      Regression Splines (MARSPlines) find the important variables that affect crude 
      oil prices. Then, the selected variables are fed into an Improved Particle Swarm 
      Optimization (IPSO) method to obtain the best estimates of the parameters of the 
      Backpropagation Neural Network (BPNN). Once these parameters are obtained, the 
      variables are fed into the BPNN model to generate the required forecasts. The 
      second approach, MARSplines-FPA-BPNN, generates the parameters of BPNN through 
      the Flower Pollination Algorithm (FPA). The forecasting ability of these new 
      models is compared to certain benchmark models. The findings document that the 
      MARSplines-FPA-BPNN model performs better than the other competitive models.
CI  - (c) 2020 Elsevier Inc. All rights reserved.
FAU - Manickavasagam, Jeevananthan
AU  - Manickavasagam J
AD  - International Management Institute, Kolkata, India.
FAU - Visalakshmi, S
AU  - Visalakshmi S
AD  - Department of Management, Central University of Tamil Nadu, Tamil Nadu, India.
FAU - Apergis, Nicholas
AU  - Apergis N
AD  - School of Business, Law and Social Sciences, University of Derby, Derby, UK.
LA  - eng
PT  - Journal Article
DEP - 20200604
PL  - United States
TA  - Technol Forecast Soc Change
JT  - Technological forecasting and social change
JID - 101085131
PMC - PMC7269956
OTO - NOTNLM
OT  - Crude oil prices
OT  - Flower Pollination model
OT  - Forecasting
OT  - Intraday data
OT  - Machine learning model
OT  - Particle Swarm Optimization model
EDAT- 2020/06/11 06:00
MHDA- 2020/06/11 06:01
PMCR- 2020/06/04
CRDT- 2020/06/11 06:00
PHST- 2019/12/19 00:00 [received]
PHST- 2020/04/02 00:00 [revised]
PHST- 2020/05/11 00:00 [accepted]
PHST- 2020/06/11 06:00 [entrez]
PHST- 2020/06/11 06:00 [pubmed]
PHST- 2020/06/11 06:01 [medline]
PHST- 2020/06/04 00:00 [pmc-release]
AID - S0040-1625(20)30952-5 [pii]
AID - 120126 [pii]
AID - 10.1016/j.techfore.2020.120126 [doi]
PST - ppublish
SO  - Technol Forecast Soc Change. 2020 Sep;158:120126. doi: 
      10.1016/j.techfore.2020.120126. Epub 2020 Jun 4.