Using GP to evolve decision rules for classification in financial data sets

Pu WANG; Edward P.K. TSANG; Thomas WEISE; Ke TANG; Xin YAO

doi:10.1109/COGINF.2010.5599820

Using GP to evolve decision rules for classification in financial data sets

Pu WANG, Edward P.K. TSANG, Thomas WEISE, Ke TANG, Xin YAO

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

5 Citations (Scopus)

Abstract

Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic Programming process itself is still very inefficient and that further improvements are necessary if we want this application of GP to become successful. © 2010 IEEE.

Original language	English
Title of host publication	Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010
Pages	720-727
Number of pages	8
DOIs	https://doi.org/10.1109/COGINF.2010.5599820
Publication status	Published - Jul 2010
Externally published	Yes

Keywords

AUC
Classification
Decision rules
EDDIE
Entropy
FGP
Finance
Forecasting
Genetic programming

Access to Document

10.1109/COGINF.2010.5599820

Cite this

@inproceedings{67fe88fb8e394c5b96c62c56af4ce326,

title = "Using GP to evolve decision rules for classification in financial data sets",

abstract = "Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic Programming process itself is still very inefficient and that further improvements are necessary if we want this application of GP to become successful. {\textcopyright} 2010 IEEE.",

keywords = "AUC, Classification, Decision rules, EDDIE, Entropy, FGP, Finance, Forecasting, Genetic programming",

author = "Pu WANG and TSANG, {Edward P.K.} and Thomas WEISE and Ke TANG and Xin YAO",

year = "2010",

month = jul,

doi = "10.1109/COGINF.2010.5599820",

language = "English",

isbn = "9781424480401",

pages = "720--727",

booktitle = "Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010",

}

Using GP to evolve decision rules for classification in financial data sets. / WANG, Pu; TSANG, Edward P.K.; WEISE, Thomas et al.
Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010. 2010. p. 720-727 5599820.

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Using GP to evolve decision rules for classification in financial data sets

AU - WANG, Pu

AU - TSANG, Edward P.K.

AU - WEISE, Thomas

AU - TANG, Ke

AU - YAO, Xin

PY - 2010/7

Y1 - 2010/7

N2 - Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic Programming process itself is still very inefficient and that further improvements are necessary if we want this application of GP to become successful. © 2010 IEEE.

AB - Financial forecasting is a lucrative and complicated application of machine learning. In this paper, we focus on the finding investment opportunities. We therefore explore four different Genetic Programming approaches and compare their performances on real-world data. We find that the novelties we introduced in some of these approaches indeed improve the results. However, we also show that the Genetic Programming process itself is still very inefficient and that further improvements are necessary if we want this application of GP to become successful. © 2010 IEEE.

KW - AUC

KW - Classification

KW - Decision rules

KW - EDDIE

KW - Entropy

KW - FGP

KW - Finance

KW - Forecasting

KW - Genetic programming

UR - http://www.scopus.com/inward/record.url?scp=78649878239&partnerID=8YFLogxK

U2 - 10.1109/COGINF.2010.5599820

DO - 10.1109/COGINF.2010.5599820

M3 - Conference paper (refereed)

SN - 9781424480401

SP - 720

EP - 727

BT - Proceedings of the 9th IEEE International Conference on Cognitive Informatics, ICCI 2010

ER -

Using GP to evolve decision rules for classification in financial data sets

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this