Outliers Treatment in Support Vector Regression for Financial Time Series Prediction

13 years 6 months ago

Download www.cse.cuhk.edu.hk

Recently, the Support Vector Regression (SVR) has been applied in the financial time series prediction. The financial data are usually highly noisy and contain outliers. Detecting outliers and deflating their influence are important but hard problems. In this paper, we propose a novel "two-phase" SVR training algorithm to detect outliers and reduce their negative impact. Our experimental results on three indices: Hang Seng Index, NASDAQ, and FSTE 100 index show that the proposed "two-phase" algorithm has improvement on the prediction.

Haiqin Yang, Kaizhu Huang, Laiwan Chan, Irwin King

Real-time Traffic

ICONIP 2004 | ICONIP 2007 | Outliers | SVR Training Algorithm | Time Series Prediction |

claim paper

» Local Support Vector Regression for Financial Time Series Prediction

» A Method for Time Series Prediction using a Combination of Linear Models

» Dynamical Modeling with Kernels for Nonlinear Time Series Prediction

» MULP A MultiLayer Perceptron Application to LongTerm OutofSample Time Series Prediction

» CostSensitive Analysis in Multiple Time Series Prediction

» Machine learning techniques in disease forecasting a case study on rice blast prediction

» Stability Bounds for Noniid Processes

» Random Forests Feature Selection with KPLS Detecting Ischemia from Magnetocardiograms

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2004
Where	ICONIP
Authors	Haiqin Yang, Kaizhu Huang, Laiwan Chan, Irwin King, Michael R. Lyu

Comments (0)

Sciweavers

Outliers Treatment in Support Vector Regression for Financial Time Series Prediction

ICONIP 2004 | ICONIP 2007 | Outliers | SVR Training Algorithm | Time Series Prediction |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers