Improving Oil Price forecasting using Regression-Relief-bases Indicators Selection Model

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Crude oil holds a vital and growing role in the local and global economy. The main goal of this study is to explore the effect of technical indicators in enhancing the capability of Sequential Minimal Optimization (SMO) to forecast the precise oil price. In addition, Relief algorithm reduces the dimensional space and eliminates irrelevant factors. 10-fold Cross validation testing method is used to train two main series of crude oil price, Brentand West Texas Intermediate (WTI). Further, Mean Absolute Error  and Root Mean Squared Error are considered as evaluation criteria. A comparison has been implemented on input features with and without TIs. The results show that using Technical Indicators satisfy better results of prediction. The Accuracy rate is raised with MAE ratio 14:1 for Brent and 15:1 for WTI, while RMSE improved with ratio17:1 for Brent and 20:1 for WTI. Finally, The experimental result proved that the optimized model was superior when compared with Linear regression, MLP regression, and Gaussian in terms of prediction errors.

     

     


  • Keywords


    SMO, Crude oil, Feature Selection, technical indicator, Ranker

  • References


      [1] J. Alvarez-Ramirez, A. Soriano, M. Cisneros, and R. Suarez, "Symmetry/anti-symmetry phase transitions in crude oil markets," Physica A: Statistical Mechanics and its Applications, vol. 322, pp. 583-596, 2003/05/01/ 2003.

      [2] P. André and W. G.C., "How volatile are crude oil prices?," OPEC Review, vol. 18, no. 4, pp. 431-444, 1994.

      [3] B. Lebaron and J. Alexandre Scheinkman, Nonlinear Dynamics and Stock Returns. 1989, pp. 311-37.

      [4] V. L. Nadh and G. S. Prasad, "Support vector machine in the anticipation of currency markets," Int. J. Eng. Technol, vol. 7, no. 2-7, p. 66, 2018.

      [5] L. Cao and F. E. H. Tay, "Financial Forecasting Using Support Vector Machines," Neural Computing & Applications, journal article vol. 10, no. 2, pp. 184-192, May 01 2001.

      [6] C. Shiyi, K. H. r. Wolfgang, and J. Kiho, "Forecasting volatility with support vector machine-based GARCH model," Journal of Forecasting, vol. 29, no. 4, pp. 406-433, 2010.

      [7] K.-j. Kim, "Financial time series forecasting using support vector machines," Neurocomputing, vol. 55, no. 1, pp. 307-319, 2003/09/01/ 2003.

      [8] Z. Xiao-lin and W. Hai-wei, "Crude Oil Prices Predictive Model Based on Support Vector Machine and Particle Swarm Optimization," Berlin, Heidelberg, 2012, pp. 645-650: Springer Berlin Heidelberg.

      [9] S. Deng and A. Sakurai, Crude Oil Spot Price Forecasting Based on Multiple Crude Oil Markets and Timeframes. 2014, pp. 2761-2779.

      [10] P. Fernandez-Blanco, D. J. Bodas-Sagi, F. J. Soltero, and J. I. Hidalgo, "Technical market indicators optimization using evolutionary algorithms," presented at the Proceedings of the 10th annual conference companion on Genetic and evolutionary computation, Atlanta, GA, USA, 2008.

      [11] M. M. Mostafa and A. A. El-Masry, "Oil price forecasting using gene expression programming and artificial neural networks," Economic Modelling, vol. 54, pp. 40-53, 2016/04/01/ 2016.

      [12] R. Samsudin and A. Shabri, "Crude oil price forecasting with an improved model based on wavelet transform and support vector machines," EJ. Artif. Intell. Comput. Sci, vol. 1, pp. 9-15, 2013.

      [13] N. I. Nwulu, "A decision trees approach to oil price prediction," in 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), 2017, pp. 1-5.

      [14] J. C. Platt, "Fast training of support vector machines using sequential minimal optimization," in Advances in kernel methods, S. Bernhard, lkopf, J. C. B. Christopher, and J. S. Alexander, Eds.: MIT Press, 1999, pp. 185-208.

      [15] A. J. Smola, B. Sch, #246, and lkopf, "A tutorial on support vector regression," Statistics and Computing, vol. 14, no. 3, pp. 199-222, 2004.

      [16] S. Pandharipande, A. Akheramka, A. Singh, and A. Shah, "Artificial Neural Network Modeling of Properties of Crude Fractions with its TBP and Source of Origin and Time," International Journal of Computer Applications, vol. 52, no. 15, 2012.

      [17] D. S. Grebenkov and J. Serror, "Following a trend with an exponential moving average: Analytical results for a Gaussian model," Physica A: Statistical Mechanics and its Applications, vol. 394, pp. 288-303, 2014/01/15/ 2014.

      [18] S. M. Nor and G. Wickremasinghe, "The profitability of MACD and RSI trading rules in the Australian stock market," Investment Management and Financial Innovations, vol. 11, no. 4, p. 194, 2014.

      [19] M. Maitah, P. Procházka, and M. Cermak, "Commodity Channel Index: Evaluation of Trading Rule of Agricultural Commodities," International Journal of Economics and Financial Issues, vol. 6, no. 1, 2016.

      [20] P. Selvam, "A study on Market Trend Prediction using “Aroon Oscillator” with special reference to the Indian private sector banks," Journal of Advance Management Research, 2017.

      [21] A. Steven B, Technical Analysis from A to Z. Chigaco: Probus Publishing, 1995.

      [22] Y. Zhang, H. Wu, and L. Cheng, "Some new deformation formulas about variance and covariance," in Modelling, Identification & Control (ICMIC), 2012 Proceedings of International Conference on, 2012, pp. 987-992: IEEE.

      [23] M. Walker Helen, Studies in the history of statistical method. The Williams And Wilkins Company; Baltimore, 1929.

      [24] Z. Bitvai and T. Cohn, "Day trading profit maximization with multi-task learning and technical analysis," Machine Learning, vol. 101, no. 1-3, pp. 187-209, 2015.

      [25] K. Kira and L. A. Rendell, "A Practical Approach to Feature Selection," presented at the Proceedings of the Ninth International Workshop on Machine Learning, 1992.


 

View

Download

Article ID: 22032
 
DOI: 10.14419/ijet.v7i4.19.22032




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.