1. NCCU Academic Hub
  2. 學術產出
  3. 社會科學學院
  4. 專書/專書篇章
  5. Item

學術產出-專書/專書篇章

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Market Microstructure: Can Dinosaurs Return? A Self-Organizing Map Approach under an Evolutionary Framework
作者 陳樹衡
Kampouridis, Michael ; Chen, Shu-Heng ; Tsang, Edward
貢獻者 經濟系
關鍵詞 Genetic Programming; Self-Organizing Maps; Market Microstructure; Market Behavior
日期 2011
上傳時間 20-三月-2014 17:07:44 (UTC+8)
摘要 This paper extends a previous market microstructure model, which investigated fraction dynamics of trading strategies. Our model consisted of two parts: Genetic Programming, which acted as an inference engine for trading rules, and Self-Organizing Maps (SOM), which was used for clustering the above rules into trading strategy types. However, for the purposes of the experiments of our previous work, we needed to make the assumption that SOM maps, and thus strategy types, remained the same over time. Nevertheless, this assumption could be considered as strict, and even unrealistic. In this paper, we relax this assumption. This offers a significant extension to our model, because it makes it more realistic. In addition, this extension allows us to investigate the dynamics of market behavior. We are interested in examining whether financial markets’ behavior is non-stationary, because this implies that strategies from the past cannot be applied to future time periods, unless they have co-evolved with the market. The results on an empirical financial market show that its behavior constantly changes; thus, agents’ strategies need to continuously adapt to the changes taking place in the market, in order to remain effective.
關聯 Applications of Evolutionary Computation Lecture Notes in Computer Science Volume 6625, 2011, pp 91-100
資料類型 book/chapter
DOI http://dx.doi.org/10.1007/978-3-642-20520-0_10
dc.contributor 經濟系en_US
dc.creator (作者) 陳樹衡zh_TW
dc.creator (作者) Kampouridis, Michael ; Chen, Shu-Heng ; Tsang, Edwarden_US
dc.date (日期) 2011en_US
dc.date.accessioned 20-三月-2014 17:07:44 (UTC+8)-
dc.date.available 20-三月-2014 17:07:44 (UTC+8)-
dc.date.issued (上傳時間) 20-三月-2014 17:07:44 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/64755-
dc.description.abstract (摘要) This paper extends a previous market microstructure model, which investigated fraction dynamics of trading strategies. Our model consisted of two parts: Genetic Programming, which acted as an inference engine for trading rules, and Self-Organizing Maps (SOM), which was used for clustering the above rules into trading strategy types. However, for the purposes of the experiments of our previous work, we needed to make the assumption that SOM maps, and thus strategy types, remained the same over time. Nevertheless, this assumption could be considered as strict, and even unrealistic. In this paper, we relax this assumption. This offers a significant extension to our model, because it makes it more realistic. In addition, this extension allows us to investigate the dynamics of market behavior. We are interested in examining whether financial markets’ behavior is non-stationary, because this implies that strategies from the past cannot be applied to future time periods, unless they have co-evolved with the market. The results on an empirical financial market show that its behavior constantly changes; thus, agents’ strategies need to continuously adapt to the changes taking place in the market, in order to remain effective.en_US
dc.format.extent 317141 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.relation (關聯) Applications of Evolutionary Computation Lecture Notes in Computer Science Volume 6625, 2011, pp 91-100en_US
dc.subject (關鍵詞) Genetic Programming; Self-Organizing Maps; Market Microstructure; Market Behavioren_US
dc.title (題名) Market Microstructure: Can Dinosaurs Return? A Self-Organizing Map Approach under an Evolutionary Frameworken_US
dc.type (資料類型) book/chapteren
dc.identifier.doi (DOI) 10.1007/978-3-642-20520-0_10en_US
dc.doi.uri (DOI) http://dx.doi.org/10.1007/978-3-642-20520-0_10 en_US