1. NCCU Academic Hub
  2. Publications
  3. College of Social Science
  4. Books & Chapters in Books
  5. Item

Publications-Books & Chapters in Books

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Is Genetic Programming ""Human-Competitive````? The Case of Experimental Double Auction Markets
作者 陳樹衡
Chen, Shu-Heng ; Shih, Kuo-Chuan
貢獻者 經濟系
關鍵詞 Experimental Markets; Double Auctions; Genetic Programming; Human-Competitiveness; Working Memory Capacity
日期 2011
上傳時間 20-Mar-2014 16:57:43 (UTC+8)
摘要 In this paper, the performance of human subjects is compared with genetic programming in trading. Within a kind of double auction market, we compare the learning performance between human subjects and autonomous agents whose trading behavior is driven by genetic programming (GP). To this end, a learning index based upon the optimal solution to a double auction market problem, characterized as integer programming, is developed, and criteria tailor-made for humans are proposed to evaluate the performance of both human subjects and software agents. It is found that GP robots generally fail to discover the best strategy, which is a two-stage procrastination strategy, but some human subjects are able to do so. An analysis from the point of view of cognitive psychology further shows that the minority who were able to find this best strategy tend to have higher working memory capacities than the majority who failed to do so. Therefore, even though GP can outperform most human subjects, it is not “human-competitive” from a higher standard.
關聯 Intelligent Data Engineering and Automated Learning - IDEAL 2011 Lecture Notes in Computer Science Volume 6936, 2011, pp 116-126
資料類型 book/chapter
DOI http://dx.doi.org/10.1007/978-3-642-23878-9_15
dc.contributor 經濟系en_US
dc.creator (作者) 陳樹衡zh_TW
dc.creator (作者) Chen, Shu-Heng ; Shih, Kuo-Chuanen_US
dc.date (日期) 2011en_US
dc.date.accessioned 20-Mar-2014 16:57:43 (UTC+8)-
dc.date.available 20-Mar-2014 16:57:43 (UTC+8)-
dc.date.issued (上傳時間) 20-Mar-2014 16:57:43 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/64753-
dc.description.abstract (摘要) In this paper, the performance of human subjects is compared with genetic programming in trading. Within a kind of double auction market, we compare the learning performance between human subjects and autonomous agents whose trading behavior is driven by genetic programming (GP). To this end, a learning index based upon the optimal solution to a double auction market problem, characterized as integer programming, is developed, and criteria tailor-made for humans are proposed to evaluate the performance of both human subjects and software agents. It is found that GP robots generally fail to discover the best strategy, which is a two-stage procrastination strategy, but some human subjects are able to do so. An analysis from the point of view of cognitive psychology further shows that the minority who were able to find this best strategy tend to have higher working memory capacities than the majority who failed to do so. Therefore, even though GP can outperform most human subjects, it is not “human-competitive” from a higher standard.en_US
dc.format.extent 445701 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.relation (關聯) Intelligent Data Engineering and Automated Learning - IDEAL 2011 Lecture Notes in Computer Science Volume 6936, 2011, pp 116-126en_US
dc.subject (關鍵詞) Experimental Markets; Double Auctions; Genetic Programming; Human-Competitiveness; Working Memory Capacityen_US
dc.title (題名) Is Genetic Programming ""Human-Competitive````? The Case of Experimental Double Auction Marketsen_US
dc.type (資料類型) book/chapteren
dc.identifier.doi (DOI) 10.1007/978-3-642-23878-9_15en_US
dc.doi.uri (DOI) http://dx.doi.org/10.1007/978-3-642-23878-9_15en_US