Forecasting the WTI crude oil price by a hybrid-refined method

Chai, Jian; Xing, Limin; Zhou, Xiaoyang; Zhang, Zhe George; Li, Jie-Xun

doi:10.1016/j.eneco.2018.02.004

Cited by 71 publications

(37 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be compared with the models developed by Azadeh. et al (2015), Chai et al (2018b), Ding, (2018 and Chen et al (2019) which may yield different results. In this study, only sixtieth minute is used, future researchers can take every fifth minute, tenth minute, fifteenth minute, and so on to compare the output of MARSplines-IPSO-BPNN and MARSplines-FPA-BPNN.…”

Section: Discussionmentioning

confidence: 99%

“…Currently, researchers are building hybrid models by combining two or more models and finding it as a successful process in minimizing the deviation between actual and predicted prices (Azadeh et al, 2015;Chai et al, 2018b;Ding, 2018;Chen et al, 2019). This motivates this paper to build novel hybrid models.…”

Section: Introductionmentioning

confidence: 99%

“…Secondly, it uses every sixtieth-minute crude oil futures contract prices of WTI and Brent to attain incremental predictability. WTI and Brent are chosen because they play an important role in stabilizing global financial markets (Chai et al, 2018b). Thirdly, in the PM-1 process, Multivariate Adaptive Regression Splines (MARSPlines) modelling helps to find the important variables that affect WTI and Brent crude oil futures prices.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel hybrid approach to forecast crude oil futures using intraday data

Manickavasagam

Visalakshmi

Apergis

2020

Technological Forecasting and Social Change

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel hybrid approach to forecast crude oil futures using intraday data

Manickavasagam

Visalakshmi

Apergis

2020

Technological Forecasting and Social Change

View full text Add to dashboard Cite

show abstract

“…The development of the world economy and the regional political dynamics amid global energy mix are mostly a factor of the volatility of crude oil price (Chai, Xing, Zhou, Zhang, & Li, 2018). This is because crude oil among other sources of energy is an important strategic commodity, thus a global market determinant.…”

Section: Energy Market Dynamicsmentioning

confidence: 99%

The dynamics of crude oil price and the real estate market in Saudi Arabia: A Markov‐switching approach

Alola

2020

Journal of Public Affairs

View full text Add to dashboard Cite

The volatility evidence of the International crude oil prices has overtime been linked to the dynamics and sector performances of states' economies. By employing the Markov switching regression model over daily time series data from October 3, 2005 to March 29, 2018, this study examines the response of the Saudi Arabia real estate market to the crude oil price dynamics. An empirical observation revealed that there is statistical evidence of significant and positive impact of crude oil price return on the real estate market in the regimes. Am empirical evidence shows that the impact is higher in Regime 2 even as the global factor (proxied by volatility index) is evidently significant. Although the regimes are persistent, the expected regime duration of the stable regime is of the higher quarter. This investigation is statistically significant and robust, especially when OPEC price of crude oil is used in lieu of the Europe Brent price. By a further estimation techniques, it affirms that the model exhibits nonlinearity rather than a linear relationship. The estimation result encourages more strict energy policies such as the implementetion of energy diversification policy among others, thus rendering a panacea to Saudi Arabia's energy and the real estate challenges.

show abstract

“…Alquist и Kilian у свом раду износе претпоставку да су цене фјучерс уговора прави показатељи цене. 2 Лам је истражио динамику нафте на основу многих економетријских модела, укључујући ARIMA модел. 3 Кроз историју су се проткали и многи радови који се баве одређивањем фундаменталних фактора који су имали утицај на цену нафте.…”

Section: преглед литературеunclassified