Financial forecasting using support vector machines

被引:278
作者
Cao, L [1 ]
Tay, FEH [1 ]
机构
[1] Natl Univ Singapore, Dept Mech & Prod Engn, Singapore 117548, Singapore
关键词
back propagation algorithm; financial time series forecasting; generalisation; multi-layer perceptron; support vector machines;
D O I
10.1007/s005210170010
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The use of Support Vector Machines (SVMs) is studied in financial forecasting by comparing it with a multi-layer perceptron trained by the Back Propagation (BP) algorithm. SVMs forecast better than BP based on the criteria of Normalised Mean Square Error (NMSE). Mean Absolute Error (MAE), Directional Symmetry (DS) Correct Up (CP) trend and Correct Down (CD) trend S&P 500 daily price index is used as the data set. Since there is no structured way to choose the free parameters of SVMs, the generalisation error with respect to the free parameters of SVMs is investigated in this experiment. As illustrated in the experiment, they have little impact on the solution. Analysis of the experimental results demonstrates that it is advantageous to apply SVMs to forecast the financial rime series.
引用
收藏
页码:184 / 192
页数:9
相关论文
共 50 条
[31]   Time Series Forecasting with Volume Weighted Support Vector Machines [J].
Zbikowski, Kamil .
BEYOND DATABASES, ARCHITECTURES AND STRUCTURES, BDAS 2014, 2014, 424 :250-258
[32]   Forecasting Electric Load by Support Vector Machines with Genetic Algorithms [J].
Pai, Ping-Feng ;
Hong, Wei-Chiang ;
Lin, Chih-Shen .
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2005, 9 (02) :134-141
[33]   An application of support vector machines to sales forecasting under promotions [J].
Di Pillo, G. ;
Latorre, V. ;
Lucidi, S. ;
Procacci, E. .
4OR-A QUARTERLY JOURNAL OF OPERATIONS RESEARCH, 2016, 14 (03) :309-325
[34]   The Quality Forecasting of Mass Customization Based on Support Vector Machines [J].
Zhao, Xiaosong ;
He, Zhen ;
Gui, Fangfang ;
Zhu, Pengfei ;
Yu, Dainuan .
IEEE/SOLI'2008: PROCEEDINGS OF 2008 IEEE INTERNATIONAL CONFERENCE ON SERVICE OPERATIONS AND LOGISTICS, AND INFORMATICS, VOLS 1 AND 2, 2008, :647-649
[35]   System reliability forecasting by support vector machines with genetic algorithms [J].
Pai, PF .
MATHEMATICAL AND COMPUTER MODELLING, 2006, 43 (3-4) :262-274
[36]   Predicting Financial Distress of Banks Using Random Subspace Ensembles of Support Vector Machines [J].
Hajek, Petr ;
Olej, Vladimir ;
Myskova, Renata .
ARTIFICIAL INTELLIGENCE PERSPECTIVES AND APPLICATIONS (CSOC2015), 2015, 347 :131-140
[37]   Financial time series forecasting using independent component analysis and support vector regression [J].
Lu, Chi-Jie ;
Lee, Tian-Shyug ;
Chiu, Chih-Chou .
DECISION SUPPORT SYSTEMS, 2009, 47 (02) :115-125
[38]   Short Term Load Forecasting Using Semi-Parametric Method and Support Vector Machines [J].
Jordaan, J. A. ;
Ukil, A. .
2009 AFRICON, VOLS 1 AND 2, 2009, :288-293
[39]   Forecasting of traffic origin NO and NO2 concentrations by Support Vector Machines and neural networks using Principal Component Analysis [J].
Juhos, Istvan ;
Makra, Laszlo ;
Toth, Balazs .
SIMULATION MODELLING PRACTICE AND THEORY, 2008, 16 (09) :1488-1502
[40]   Drainage water level classification using support vector machines [J].
Rao, Tarun ;
Rajasekhar, N. ;
Rajinikanth, T. V. .
2013 4TH NIRMA UNIVERSITY INTERNATIONAL CONFERENCE ON ENGINEERING (NUICONE 2013), 2013,