Constructing generalized exponential predictors via penalty methods: empirical analysis on gold price

doi:10.7523/j.issn.2095-6134.2012.2.003

Abstract

Abstract:

We construct generalized exponential predictors for forecasting gold price using different loss and penalty functions. The construction methods include: 1) ridge regression and 2) selection of linear combinations of EWMA predictors with different parameters by adding LASSO and SCAD penalties based on L₁,L₂ and the L_M loss function which combines both L₁ and L₂. Practical data show that our models improve the single parameter EWMA model effectively and they perform better than the models suggested in the literature.

Key words: generalized exponential predictors, gold price forecast, variable selection, penalty functions, loss function

CLC Number:

F224.7

YAN Wei, YIN Wei, MIAO Bai-Qi, YE Wu-Yi. Constructing generalized exponential predictors via penalty methods: empirical analysis on gold price[J]. , 2012, (2): 162-168.

References

[1] Zhang G P, Patuwo E B, Hu M Y. A simulation study of artificial neural networks for nonlinear time series forecasting[J]. Computers and Operations Research, 2001, 28: 381-396.
[2] Cao L J, Tay F E H. Financial forecasting using support vector machines[J]. Neural Computing Applications, 2001, 10:184-192.
[3] Wang S, Yu L, Lai K. Crude oil price forecasting with TEI@I methodology[J]. Journal of Systems Science & Complexity, 2005, 18(2): 145-166.
[4] Selvanathan E A. A note on the accuracy of business economists’ gold price forecasts[J]. Australian Journal of Management, 1991,16(1):91-94.
[5] Wang C B, Chen Y H, Li L H. The forecast of gold price based on the GM(1, 1) and markov chain //Proceedings of 2007 IEEE International Conference on Grey Systems and Intelligent Services. Nanjing, China, 2007.
[6] Tzou Y P, Hu H N, Cheng W X. The variety applications in asymmetric power GARCH model[J]. Soochow Journal of Economics and Business, 2008,63: 29-52(in Chinese). 鄒易憑,胡緒甯,鄭婉秀. 不對稱冪級數GARCH模型之多樣化應用[J]. 東吳經濟商學學報, 2008,63: 29-52.
[7] Antonino P, Franco P, David D. Forecasting gold price changes: Rolling and recursive neural network models[J]. Journal of Multinational Financial Management, 2008,18: 477-487.
[8] Ismail Z, Yahya A, Shabri A. Forecasting gold prices using multiple linear regression method[J]. American Journal of Applied Sciences, 2009,6 (8): 1509-1514.
[9] Huang S J, Zhang D S, Chang Z H, et al. FAR forecast model of international gold prices based on wavelet analysis[J]. Journal of Xi’an Institute of Technology, 2009, 29(1): 84-88(in Chinese). 黄师娟,张德生,常振华,等. 国际黄金价格的小波变换FAR预测模型[J]. 西安工业大学学报, 2009, 29(1): 84-88.
[10] Lin Y, Kong L L, Liu P. The gold price forecasts based on the ARFIMA model[J]. Journal of Nanhua University, 2010, 11(1): 36-38(in Chinese). 林雨,孔刘柳,刘培. 基于AFIMA模型的黄金价格预测[J]. 南华大学学报, 2010, 11(1): 36-38.
[11] Burman P, Shumway R H. Generalized exponential predictors for time series forecasting[J]. Journal of the American Statistical Association, 2006, 101:1598-1606.
[12] Qin P, Miao B Q. Crude oil price forecasting model based on generalized exponential predictors[J]. Systems Engineering—Theory & Practice, 2010, 30(8):1389-1395(in Chinese). 秦鹏,缪柏其. 基于广义指数预报因子的石油价格预测模型[J]. 系统工程理论与实践, 2010, 30(8):1389-1395.
[13] Breiman L. Better subset regression using the nonnegative garrote[J]. Technometrics, 1995, 37: 373-384.
[14] Fan J, Li R. Variable selection via nonconcave penalized likelihood and its oracle properties[J]. Journal of American Statistical Association, 2001, 96:1348-1360.
[15] Tibshirani R J. Regression shrinkage and selection via the LASSO[J]. Journal of the Royal Statistical Society, 1996, Ser B, 58:267-288.
[16] 陈希孺. 最小一乘线性回归(上)[J]. 数理统计与管理, 1989,5: 48-55.
[17] Li R Z, Lin Dennis K J. Data analysis in supersaturated designs[J]. Statistics & Probability Letters,2002, 59: 135-144.
[18] Zou H,Hastie Trevor.Regularization and variable selection via the elastic net[J].Journal of the Royal Statistical Society,2005,67:301-320.
[19] Ramazan S,Shawka H,Ugur S.Dynamics of oil price,precious metal prices,and exchange rate[J].Energy Economics,2010,32:351-362.