Please use this identifier to cite or link to this item: https://ah.nccu.edu.tw/handle/140.119/68715


Title: Overfitting or Poor Learning : A Critique of Current Financial Applications of GP
Authors: 陳樹衡
Chen,Shu-Heng
Contributors: 經濟系
Date: 2003
Issue Date: 2014-08-14 11:43:23 (UTC+8)
Abstract: Motivated by a measure of predictability, this paper uses the extracted signal ratio as a measure of the degree of overfitting. With this measure, we examine the performance of one type of overfittingavoidance design frequently used in financial applications of GP. Based on the simulation results run with the software Simple GP, we find that this design is not effective in avoiding overfitting. Furthermore, within the range of search intensity typically considered by these applications, we find that underfitting, instead of overfitting, is the more prevalent problem. This problem becomes more serious when the data is generated by a process that has a high degree of algorithmic complexity. This paper, therefore, casts doubt on the conclusions made by those early applications regarding the poor performance of GP, and recommends that changes be made to ensure progress.
Relation: Genetic Programming Lecture Notes in Computer Science Volume 2610, 2003, pp 34-46
Data Type: book/chapter
DOI 連結: http://dx.doi.org/10.1007/3-540-36599-0_4
Appears in Collections:[經濟學系] 專書/專書篇章

Files in This Item:

File Description SizeFormat
6599.pdf297KbAdobe PDF1060View/Open


All items in 學術集成 are protected by copyright, with all rights reserved.


社群 sharing