Forecasting model for crude oil prices based on artificial neural networks

Haidar, Imad; Kulkarni, Siddhivinayak; Pan, Heping

doi:10.1109/issnip.2008.4761970

Cited by 42 publications

(25 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The neural network arbitrage strategy focuses on the research object's volatility, thus making arbitrage strategies. Haider et al (2008) [14] used artificial neural network model to predict the oil futures market, and found that using artificial neural network to develop arbitrage strategy could help to improve the yield. Phoebe and David (2014) [15] using the RBF neural network, LM neural network model for soybean meal, soybean oil, soybean and its squeezing goods spread analysis predicted the short-term fluctuations, thinking that traders could according to the forward contracts affected the recent contract squeezing spreads profit carry this phenomenon.…”

Section: Advances In Computer Science Research Volume 82mentioning

confidence: 99%

Research on Futures Arbitrage Based on Iron Ore Futures

Wang¹

2017

Proceedings of the 2017 7th International Conference on Social Network, Communication and Education (SNCE 2017)

View full text Add to dashboard Cite

Abstract. Steel industry is one of the pillar industries of China's national economy, while the iron ore is the main raw material for smelting steel. China is rich in iron ore resources, but less in rich iron ore, which results in the difficulty and high cost of the use of iron ore. Therefore, the main source of China's iron ore relies on import, at the same time, China becomes the largest production and consumption country. This paper studies domestic and foreign achievements of futures arbitrage from aspects of arbitrage methods and arbitrage strategies, and classifies these literatures. We should consider the price volatility of iron ore futures and the long-term equilibrium relationship with the other relative futures.

show abstract

Section: Advances In Computer Science Research Volume 82mentioning

confidence: 99%

Research on Futures Arbitrage Based on Iron Ore Futures

Wang¹

2017

Proceedings of the 2017 7th International Conference on Social Network, Communication and Education (SNCE 2017)

View full text Add to dashboard Cite

show abstract

“…The main reason is attributed to the irregularity and the sudden abrupt changes in the oil price behavior that marked the last three decades [19]. Specifically, the prediction will inevitably be incomplete, as the network representation of the relationships between oil prices and the respective factors require an explicit mapping [20].…”

Section: Feature Selection For Forecastingmentioning

confidence: 99%

“…Crude oil prices prediction is not an easy task because there are many factors that can influence their tendency such government interventions, political events, weather conditions, financial speculations, supply, inventories, demand, exchange rates, OPEC oil policy, GDP, financial shocks, price trends and stock market, dollar index, gold, heating oil spot price, etc. [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Oil price prediction using ensemble machine learning

Gabralla

Jammazi

Abraham

2013

2013 International Conference on Computing, Electrical and Electronic Engineering (Icceee)

View full text Add to dashboard Cite

Abstract-Crude oil price forecasting is a challenging task due to its complex nonlinear and chaotic behavior. During the last couple of decades, both academicians and practitioners devoted proactive knowledge to address this issue. A strand of them has focused on some key factors that may influence the crude oil price prediction accuracy. This paper extends this particular branch of recent works by considering a number of influential features as inputs to test the forecasting performance of daily WTI crude oil price covering the period 4th January 1999 through 10th October 2012. Empirical results indicate that the proposed methods are efficient and warrant further research in this field.

show abstract

“…Some machine learning methods such as artificial neural networks (ANNs) and support vector machines (SVM) were proposed to solve the nonlinearity problems of time series and gave better results than conventional methods. For example, many researchers applied ANN based models [11][12][13][14]. Pierdzioch et al [15,16] forecasted oil price under asymmetric loss and found new evidence of anti-herding of oil price forecasters.…”

Section: Introductionmentioning

confidence: 99%

Crude Oil Spot Price Forecasting Based on Multiple Crude Oil Markets and Timeframes

Sakurai

2014

Energies

View full text Add to dashboard Cite

This study proposes a multiple kernel learning (MKL)-based regression model for crude oil spot price forecasting and trading. We used a well-known trend-following technical analysis indicator, the moving average convergence and divergence (MACD) indicator, for extracting features from original spot prices. Additionally, we factored in the possibility that movements of target crude oil prices may be related to other important crude oil markets besides the target market for the prediction time horizon since traders may find price movement information within other relevant crude oil markets useful. We also considered multiple timeframes in this study since trends may differ across different timeframes and, in fact, traders may use their own timeframes. Therefore, for forecasting target crude oil prices, this study emphasizes on features pertaining to other important crude oil markets and different timeframes in addition to features of the target crude oil market and target timeframe. Moreover, the MKL framework has been used to fuse information extracted from different sources and timeframes of the same data source. Experimental results show that out-of-sample forecasting using the MKL method is superior to benchmark methods in terms of root mean square error (RMSE) and average percentage profit (APP). They also show that the information from multiple timeframes is useful for prediction, but that from another crude oil market is not.

show abstract

Forecasting model for crude oil prices based on artificial neural networks

Cited by 42 publications

References 15 publications

Research on Futures Arbitrage Based on Iron Ore Futures

Research on Futures Arbitrage Based on Iron Ore Futures

Oil price prediction using ensemble machine learning

Crude Oil Spot Price Forecasting Based on Multiple Crude Oil Markets and Timeframes

Contact Info

Product

Resources

About