Abstract
This paper proposes a novel approach to overcome the bottleneck in financial data mining. We construct a composite kernel machine (CKM) on the kernel local fisher discriminant space (KLFDS) to solve three problems in high-dimensional data mining: the curse of dimensionality, data complexity and nonlinearity. CKM exploits multiple data sources with strong capability to identify the relevant ones and their apposite kernel representation. KLFDS is an optimal projection of original data to a low dimensional space which maximizes the margin between data points from different classes at each local area of data manifold. Our new system robustly overcomes the weakness of CKM, it outperforms many traditional classification systems.
Original language | English |
---|---|
Title of host publication | IET International Conference on Information and Communications Technologies, IETICT 2013 |
Pages | 58-63 |
Number of pages | 6 |
Volume | 2013 |
Edition | 618 CP |
Publication status | Published - 2013 Dec 1 |
Event | IET International Conference on Information and Communications Technologies, IETICT 2013 - Beijing, China Duration: 2013 Apr 27 → 2013 Apr 29 |
Other
Other | IET International Conference on Information and Communications Technologies, IETICT 2013 |
---|---|
Country | China |
City | Beijing |
Period | 13-04-27 → 13-04-29 |
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering