A Novel Look Back N Feature Approach towards Prediction of Crude Oil Price

  • Authors

    • Rudra Kalyan Nayak
    • Kuhoo .
    • Debahuti Mishra
    • Amiya Kumar Rath
    • Ramamani Tripathy
    2018-09-01
    https://doi.org/10.14419/ijet.v7i3.34.19360
  • Support Vector Machine (SVM), k-nearest neighbor (k-NN), Grey wave forecasting method, autoregressive integrated moving average (ARIMA), Look Back N Feature (LBNF).
  • Prediction of crude oil prices in advance can play a significant role in the global economy. Change in crude oil price affect wide range of application for economic and risk projection. Crude oil price forecasting is a challenging task due to its complex nonlinear and chaotic behavior. During the last decade’s researcher have designed many classification algorithm for crude oil prediction. The major challenge for any unsupervised dataset is to define a class label for every feature of its dataset. This paper, propose a new novel technique, look back N feature (LBNF) algorithm to discover class label. Later the classifier support vector machine (SVM) with k-nearest neighbor (k-NN) has been used to classify the current feature vector to predict the crude indices one day, one weak, one month in advance. We have checked our algorithm with standard recent MCX INR Daily and CFD USD Real Time crude oil dataset. To prove the effectiveness of proposed algorithm we have compared it with recent Grey wave forecasting method and the experimental result is found to be better than this method.

     

  • References

    1. [1] Natural resources - definition of natural resources in English, Oxford Dictionaries. 2014-04-20. Retrieved 2016-12-12. https://en.wikipedia.org/wiki/Natural_resource.

      [2] Guerriero V, Mazzoli S, Iannace A, Vitale S, Carravetta A & Strauss C, “A permeability model for naturally fractured carbonate reservoirsâ€, Marine and Petroleum Geology, Vol. 40, (2013), pp. 115-134.

      [3] Azoff EM, Neural network time series forecasting of financial markets, John Wiley & Sons, Inc. (1994).

      [4] Haidar I, Kulkarni S & Pan H, “Forecasting model for crude oil prices based on artificial neural networksâ€, International Conference on Intelligent Sensors, Sensor Networks and Information Processing, (2008), pp. 103-108.

      [5] Haykin S, Neural networks, a comprehensive foundation, (1994).

      [6] Yu L, Wang S & Lai KK, “Forecasting crude oil price with an EMD-based neural network ensemble learning paradigmâ€, Energy Economics, Vol. 30, No. 5, (2008), pp. 2623-2635.

      [7] Kulkarni S & Haidar I, “Forecasting model for crude oil price using artificial neural networks and commodity futures pricesâ€, arXiv preprint arXiv: 0906.4838, (2009).

      [8] Pan H, Haidar I & Kulkarni S, “Daily prediction of short-term trends of crude oil prices using neural networks exploiting multimarket dynamicsâ€, Frontiers of Computer Science in China, Vol. 3, No. 2, (2009), pp. 177-191.

      [9] Abdullah SN & Zeng X, “Machine learning approach for crude oil price prediction with Artificial Neural Networks-Quantitative (ANN-Q) modelâ€, The 2010 International Joint Conference on Neural Networks (IJCNN), (2010), pp. 1-8.

      [10] Chen X & Qu Y, “A prediction method of crude oil output based on artificial neural networksâ€, Proc. of the IEEE Int. Conf. Comput. Inf. Sci, (2011), pp. 702-704.

      [11] Gunawan R, Khodra ML, “Commodity price prediction using neural network case study: Crude palm oil priceâ€, International Conference on Computer, Control, Informatics and Its Applications (IC3INA), (2013), pp. 243-248.

      [12] Gunawan R & Khodra ML, “Commodity price prediction using neural network case study: Crude palm oil priceâ€, International Conference on Computer, Control, Informatics and Its Applications (IC3INA), (2013), pp. 243-248.

      [13] Xu D, Zhang Y, Cheng C, Xu W & Zhang L, “A neural network-based ensemble prediction using PMRS and ECMâ€, 47th Hawaii International Conference on System Sciences, (2014), pp. 1335-1343.

      [14] Abubakar AI, Chiroma H & Abdulkareem S, “Comparing performances of neural network models built through transformed and original dataâ€, International Conference on Computer, Communications, and Control Technology, (2015), pp. 364-369.

      [15] Xie W, Yu L, Xu S & Wang S, “A new method for crude oil price forecasting based on support vector machinesâ€, International Conference on Computational Science, (2006), pp. 444-451.

      [16] Bao Y, Yang Y, Xiong T & Zhang J, “A comparative study of multi-step-ahead prediction for crude oil price with support vector regressionâ€, Fourth International Joint Conference on Computational Sciences and Optimization (CSO), (2011), pp. 598-602.

      [17] Khashman A & Nwulu NI, “Intelligent prediction of crude oil price using Support Vector Machinesâ€, IEEE 9th International Symposium on Applied Machine Intelligence and Informatics (SAMI), (2011), pp. 165-169.

      [18] Fan L, Pan S, Li Z & Li H, “An ICA-based support vector regression scheme for forecasting crude oil pricesâ€, Technological Forecasting and Social Change (2016).

      [19] Behmiri NB & Manso JRP, “Crude oil price forecasting techniques: a comprehensive review of literatureâ€, CAIA Alternative Investment Analyst Review, Vol. 2, No. 3, (2013), pp. 30-48.

      [20] Yu L, Dai W & Tang L, “A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecastingâ€, Engineering Applications of Artificial Intelligence, Vol. 47, (2016), pp. 110-121.

      [21] Yu L, Wang S, Wen B & Lai KK, “An AI-agent-based trapezoidal fuzzy ensemble forecasting model for crude oil price predictionâ€, 3rd International Conference on Innovative Computing Information and Control, IEEE, (2008), pp. 327-327.

      [22] Behmiri NB, Manso JRP, “Crude Oil Price Forecasting Techniques: A Comprehensive Review of Literature†(2013).

      [23] He Angela WW, Kwok Jerry TK & Wan Alan TK, “An empirical model of daily highs and lows of West Texas Intermediate crude oil pricesâ€, Energy Economics, Vol. 32, No. 6, (2010), pp. 1499-1506.

      [24] Ekaterini P & Theologos P, “Speculative behaviour and oil price predictabilityâ€, Economic Modelling. Vol. 47, (2015), pp. 128-136.

      [25] Atilim M & Ekin T, “Forecasting oil price movements with crack spread futuresâ€, Energy Economics, Vol. 31, No. 1, (2009), pp. 85-90.

      [26] Lean Y, Shouyang W & Keung LK, “Forecasting crude oil price with an EMD-based neural network ensemble learning paradigmâ€, Energy Economics, Vol. 30, No. 5, (2008), pp. 2623-2635.

      [27] Kaijian H, Lean Y & Keung LK, “Crude oil price analysis and forecasting using wavelet decomposed ensemble modelâ€, Energy. 2012, Vol. 46, No. 1, (2012), pp. 564-574.

      [28] Ziran L, Jiajing S & Shouyang W, “An information diffusion-based model of oil futures priceâ€, Energy Economics, Vol. 36, (2013), pp. 518-525.

      [29] Chen Y, Zou Y, Zhou Y & Zhang C, “Multi-step-ahead Crude Oil Price Forecasting based on Grey Wave Forecasting Methodâ€, Procedia Computer Science, Vol. 91, (2016), pp. 1050-1056.

      [30] Van Der Walt C & Barnard E, “Data characteristics that determine classifier performanceâ€, (2006).

      [31] http://in.investing.com/commodities/crude-oil

      [32] Manescu C & Robays IV, “Forecasting the Brent oil price: addressing time-variation in forecast performanceâ€, (2014).

      [33] Chiroma H, Abdulkareem S & Herawan T, “Evolutionary Neural Network model for West Texas Intermediate crude oil price predictionâ€, Applied Energy, Vol. 142, (2015), pp. 266-273.

      [34] Beckers B, “Forecasting the Nominal Brent Oil Price with VARs—One Model Fits All?â€, International Monetary Fund, (2015).

      [35] Magda B & Fayek, “Multi-objective optimization of technical stock market indicators using gasâ€, Int. J. Comput. Appl, 0975-8887, Vol. 68, No. 20, (2013).

      [36] http://stockcharts.com/school/doku.php?id=chart school:technicalindicators:williams r

      [37] Moldovan D, Moca M & Nitchi S, “A stock trading algorithm model proposal, based on technical indicators signalsâ€, Informatica Economica, Vol. 15, No. 1, (2011), pp. 183.

      [38] Nayak RK, Mishra D & Rath AK, “A Naïve SVM-KNN based stock market trend reversal analysis for Indian benchmark indicesâ€, Applied Soft Computing, Vol. 35, (2015), pp. 670-680.

      [39] Jayasinghe GK, Culpepper JS & Bertok P, “Efficient and effective realtime prediction of drive-by download attacksâ€, Journal of Network and Computer Applications, Vol. 38, (2014), pp. 135-149.

  • Downloads

  • How to Cite

    Kalyan Nayak, R., ., K., Mishra, D., Kumar Rath, A., & Tripathy, R. (2018). A Novel Look Back N Feature Approach towards Prediction of Crude Oil Price. International Journal of Engineering & Technology, 7(3.34), 459-465. https://doi.org/10.14419/ijet.v7i3.34.19360