The Influence of Training Step on Price Forecasting Based on Support Vector Machine

Abstract:

In order to obtain suit commodity price forecasting model and help consumers have the better reference resources when they buy mobile phones, cell phones price forecasting on training step is discussed in this paper. One year price for ten types mobile phone which extracted from http://www.jd.com/ is used as the original data to improve Support Vector Machine (SVM) model based on the training step. According to this forecasting method, the experiments are implemented under the different training step for different types cell phones depend on the accuracy rata. Comparing the experimental results with the original data, the forecasting average accuracy obtains 94.48 percent. But with the training step growth, the efficiency of model is cutting down unceasingly. Experiment results prove that the research is meaningful and useful and it is not only for consumers, but also for businesses in the cell phones market.

• Periodical: Applied Mechanics and Materials (Volumes 411-414)
• Pages: 2373-2376
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.411-414.2373
• Online since: September 2013
• Authors: Lu Pan, Sheng Ji Rong, Chang Hui Yu, Chun Xia Jin, Quan Yin Zhu*
• Keywords: Price Forecasting, Support Vector Machine (SVM), Training Step

References

[1] CHANG Song, HE Jinmen: Stock price forecasting model based on wavelet packet and neural network. Chinese Journal of Management Science, 2001, 9( 5) : 8-15.

[2] ZHANG Hengyang, LIN Hui: Option price forecasting model by applying hybrid neural network and genetic algorithm. Journal of Industrial Engineering and Engineering Management, 2009, 23( 1) : 59-62.

[3] LEE S H, LIME J S: Forecasting exchange rate by weighted average defuzzification based on NEWFM. IEEE International Conference on Industrial Informatics. Daejeon: Institute of Electrical and Electronics Engineers Inc. 2008: 1036-1041.

DOI: 10.1109/indin.2008.4618255

[4] WANG Hua, LIU Bingxiang, CHENG Xiang: An exchange rate forecasting method based on probabilistic neural network. International Conference on Electronic and Mechanical Engineering and Information Technology. Harbin: IEEE Computer Society, 2011: 31243126.

DOI: 10.1109/emeit.2011.6023749

[5] YANG Hengli, LIN Hanchou: Applying EMD-based neural network to forecast NTD / USD exchange rateInternational Conference on Networked Computing and Advanced Information Management. Daejeon: IEEE Computer Society，2011: 352-357.

[6] Pindoriya N M, Singh S N and Singh S K: An Adaptive Wavelet Neural Network-Based Energy Price Forecasting in Electricity Markets. IEEE Transactions on Power Systems, 23 (2008): 1423 – 1432.

DOI: 10.1109/tpwrs.2008.922251

[7] WU Hong, CHEN Fuzhong: Chinese exchange rate forecasting based on the application of grey system DGM(2, 1) model in postcrisis era International Conference on Information Management. Innovation Management and Industrial Engineering. Kunming: IEEE Computer Society, 2010: 592-595.

DOI: 10.1109/iciii.2010.147

[8] Xiaojuan, Ban, Qilong, Shen: Compression method based on training dataset of SVM. Journals & Magazines, University of Science & Technology Beijing, Feb. 2008, 10. 1016/ S1004-4132(08)60067-5, P198 – 201.

[9] Lucidi, S. ; Dipt. di Inf. e Sist: A Convergent Hybrid Decomposition Algorithm Model for SVM Training. Journals & Magazines. Sapienza Univ. di Roma, June 2009, 10. 1109/ TNN. 2009. 2020908, P 1055 - 1060.

[10] Jian-xiong Dong, Devroye L: Fast SVM training algorithm with decomposition on very large data sets. Journals & Magazines. Concordia Univ. April 2005, 10. 1109/TPAMI. 2005. 77, P 603 – 618. June 2009, 10. 1109/TGRS. 2008. 2007128, P 1707 – 1718.

DOI: 10.1109/tpami.2005.77

[11] CAO Lijuan, Tay F E H: Financial forecasting using support vector machines . Neural Computing & Applications, 2001, 10(2): 184 - 192.

DOI: 10.1007/s005210170010

[12] Ghoggali, N.; Melgani, F: A Multiobjective Genetic SVM Approach for Classification Problems With Limited Training Samples. Journals & Magazines. Univ. of Trento. June 2009, 10. 1109/TGRS. 2008. 2007128, P 1707 – 1718.

DOI: 10.1109/tgrs.2008.2007128

[13] Vapnic VN: The nature of statistical learning theory. New York: Springer-Verlag, (1995).

[14] Suykens J, Vandewalle J: Least square support vector machine classifiers. Neural Processing Letters, 9(3). 1999: 293-300.

[15] ZhenRui Peng, PU Gao, JianJun Meng, WenZhe Qi: A PRELIMINARY STUDY OF AIRPORT FREIGHT TRAFFIC FORECASTING BASED ON LEAST SQUARES SUPPORT VECTOR MACHINE. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, 2005: 3680-3685.

DOI: 10.1109/icmlc.2005.1527580

[16] WANG Yongjie, WANG Liyuan, ZHANG Hengxi: The purchasing price prediction of aircraft based on hierarchical partial least squares regression. Fire Control＆ Command Control, 2010, 35( 10) : 98-101.

[17] Zhu Quanyin, Pan Lu, Yan Yunyang, Gu Tianfeng: Data Normalization for Original Data on Price Forecasting. International Journal of Computer Science and Application (IJCSA). 2013. Vol. 2(3).