Financial forecasting using support vector machines

被引：277

作者：

Cao, L ^{[1
]}

Tay, FEH ^{[1
]}

机构：

[1] Natl Univ Singapore, Dept Mech & Prod Engn, Singapore 117548, Singapore

来源：

NEURAL COMPUTING & APPLICATIONS | 2001年 / 10卷 / 02期

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

页码：184 / 192

页数：9

共 50 条

[41] Wind direction forecasting with artificial neural networks and support vector machines [J].

Tagliaferri, F. ;

Viola, I. M. ;

Flay, R. G. J. .

OCEAN ENGINEERING, 2015, 97 :65-73

[42] Support vector machines for short-term electrical load forecasting [J].

Mohandes, M .

INTERNATIONAL JOURNAL OF ENERGY RESEARCH, 2002, 26 (04) :335-345

[43] Multi-scaled Forecasting Model Based on Support Vector Machines [J].

Qu, Wenlong ;

Li, Ning ;

He, Yichao ;

Qu, Wenjing .

2010 2ND INTERNATIONAL WORKSHOP ON DATABASE TECHNOLOGY AND APPLICATIONS PROCEEDINGS (DBTA), 2010,

[44] Software reliability forecasting by support vector machines with simulated annealing algorithms [J].

Pai, Ping-Feng ;

Hong, Wei-Chiang .

JOURNAL OF SYSTEMS AND SOFTWARE, 2006, 79 (06) :747-755

[45] Power Load Forecasting Based on the Locally Weighted Support Vector Machines [J].

Cai Yongming ;

Zhao Shuhai .

MANAGEMENT ENGINEERING AND APPLICATIONS, 2010, :383-387

[46] Forecasting Transport Mode Use with Support Vector Machines Based Approach [J].

Semanjski, Ivana ;

Lopez, Angel J. ;

Gautama, Sidharta .

TRANSACTIONS ON MARITIME SCIENCE-TOMS, 2016, 5 (02) :111-120

[47] Regularized least squares fuzzy support vector regression for financial time series forecasting [J].

Khemchandani, Reshma ;

Jayadeva ;

Chandra, Suresh .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (01) :132-138

[48] A hybrid ARIMA and support vector machines model in stock price forecasting [J].

Pai, PF ;

Lin, CS .

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 2005, 33 (06) :497-505

[49] Some evidence on forecasting time-series with support vector machines [J].

Hansen, J. V. ;

McDonald, J. B. ;

Nelson, R. D. .

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2006, 57 (09) :1053-1063

[50] Effective training of support vector machines using extractive support vector algorithm [J].

Yao, Chih-Chia ;

Yu, Pao-Ta .

PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2007, :1808-+

← 1 2 3 4 5 →