東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Architecting system of systems: Arti...

Ergin, Nil Hande.

FindBook

Google Book

Amazon

博客來

Architecting system of systems: Artificial life analysis of financial market behavior.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Architecting system of systems: Artificial life analysis of financial market behavior./
作者:	Ergin, Nil Hande.
面頁冊數:	138 p.
附註:	Advisers: C. H. Dagli; D. Enke.
Contained By:	Dissertation Abstracts International69-01B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3298470
ISBN:	9780549429227

Architecting system of systems: Artificial life analysis of financial market behavior.
Ergin, Nil Hande.

Architecting system of systems: Artificial life analysis of financial market behavior. - 138 p.

Advisers: C. H. Dagli; D. Enke.

Thesis (Ph.D.)--University of Missouri - Rolla, 2007.

Today's systems typically do not stand alone in isolation. Often a system fits within a System of Systems, a network of interconnected systems that often exhibits unpredictable behavior. This study is motivated by the challenges of understanding the emergent system level behavior of System of Systems given the opaque characteristics of social processes and continuously changing operating and environmental conditions. An artificial life based framework for modeling System of Systems is presented as an analysis technique. The framework comprises cognitive architectures embedded in multi-agent models. Financial markets are selected as an analysis domain to demonstrate the framework since they are a good example of self-organizing systems that exhibit System of Systems characteristics, specifically emergence on a grand scale. The effects of different mechanisms on system level market dynamics are analyzed. In particular, the effects of the covering mechanism, learning mechanism and bias mechanism are analyzed. A trader-based architecture is proposed to formulate a trader decision model that combines bias mechanisms with learning mechanisms. A prediction accuracy based Learning Classifier System is used to model the trader learning mechanism. Markov processes are utilized to model the bias mechanism of traders. Simulation experiments are generated using the Anylogic5.1(TM) software. Homogenous rational expectations equilibrium is utilized as the benchmark for comparison of results from the hybrid proposed model. The model derived from the framework contributes to understanding the market behavior and potential sources of deviation from efficient market equilibrium. The artificial life based framework provides a flexible way of modeling sub-systems of System of Systems and captures the adaptive and emergent behavior of the system.

ISBN: 9780549429227Subjects--Topical Terms:

769149
Artificial Intelligence.

Architecting system of systems: Artificial life analysis of financial market behavior.
LDR:02813nam 2200301 a 45 001 959004
005 20110704
008 110704s2007 ||||||||||||||||| ||eng d
020 $a 9780549429227
035 $a (UMI)AAI3298470
035 $a AAI3298470
040 $a UMI $c UMI
100 1 $a Ergin, Nil Hande. $3 1282472
245 1 0 $a Architecting system of systems: Artificial life analysis of financial market behavior.
300 $a 138 p.
500 $a Advisers: C. H. Dagli; D. Enke.
500 $a Source: Dissertation Abstracts International, Volume: 69-01, Section: B, page: 0650.
502 $a Thesis (Ph.D.)--University of Missouri - Rolla, 2007.
520 $a Today's systems typically do not stand alone in isolation. Often a system fits within a System of Systems, a network of interconnected systems that often exhibits unpredictable behavior. This study is motivated by the challenges of understanding the emergent system level behavior of System of Systems given the opaque characteristics of social processes and continuously changing operating and environmental conditions. An artificial life based framework for modeling System of Systems is presented as an analysis technique. The framework comprises cognitive architectures embedded in multi-agent models. Financial markets are selected as an analysis domain to demonstrate the framework since they are a good example of self-organizing systems that exhibit System of Systems characteristics, specifically emergence on a grand scale. The effects of different mechanisms on system level market dynamics are analyzed. In particular, the effects of the covering mechanism, learning mechanism and bias mechanism are analyzed. A trader-based architecture is proposed to formulate a trader decision model that combines bias mechanisms with learning mechanisms. A prediction accuracy based Learning Classifier System is used to model the trader learning mechanism. Markov processes are utilized to model the bias mechanism of traders. Simulation experiments are generated using the Anylogic5.1(TM) software. Homogenous rational expectations equilibrium is utilized as the benchmark for comparison of results from the hybrid proposed model. The model derived from the framework contributes to understanding the market behavior and potential sources of deviation from efficient market equilibrium. The artificial life based framework provides a flexible way of modeling sub-systems of System of Systems and captures the adaptive and emergent behavior of the system.
590 $a School code: 0135.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Economics, Finance. $3 626650
650 4 $a Engineering, System Science. $3 1018128
690 $a 0508
690 $a 0790
690 $a 0800
710 2 $a University of Missouri - Rolla. $3 1025712
773 0 $t Dissertation Abstracts International $g 69-01B.
790 $a 0135
790 1 0 $a Dagli, C. H., $e advisor
790 1 0 $a Enke, D., $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3298470