Using GP to Evolve Decision Rules for Classification in Financial Data Sets

Authors

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.

Keywords

Classification, Genetic Programming, GP, Decision Trees, Data Mining, Economics/Finances

BibTeX

@inproceedings{WTWTY2010UGTEDRFCIFDS,
  author                    = {P{\'{u}} W{\'{a}}ng and Edward P. K. Tsang and Thomas Weise and K{\={e}} T{\'{a}}ng and X{\={\i}}n Y{\'{a}}o},
  title                     = {{Using GP to Evolve Decision Rules for Classification in Financial Data Sets}},
  booktitle                 = {Proceedings of the 9th IEEE International Conference on Cognitive Informatics (ICCI'10)},
  editor                    = {Fuchun Sun and Yingxu Wang and Jianhua Lu and Bo Zhang and Witold Kinsner and Lotfi A. Zadeh},
  publisher                 = {{IEEE Computer Society Press: {Los Alamitos, CA, USA}}},
  pages                     = {722--727},
  year                      = {2010},
  location                  = {{Tsinghua University: {B{\v{e}}ij{\={\i}}ng, China}}},
  url                       = {http://mail.ustc.edu.cn/~wuyou308/paper1.pdf},
  doi                       = {10.1109/COGINF.2010.5599820},
  key                       = {WTWTY2010UGTEDRFCIFDS},
},

Links