東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Behavioral Financial Network: An Age...

Alsulaiman, Talal.

Linked to FindBook

Google Book

Amazon

博客來

Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets./
Author:	Alsulaiman, Talal.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	244 p.
Notes:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
Subject:	Systems science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10688507
ISBN:	9780355744262

Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets.
Alsulaiman, Talal.

Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 244 p.

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--Stevens Institute of Technology, 2017.

Artificial financial markets (AFMs) aim to investigate the link between individual behaviors and financial market dynamics. The financial market is a complex system in which the relation between its components cannot be captured analytically. Computational approaches, such as simulation, are needed to comprehend this relation. A common method used to build AFMs is the agent-based simulation.

ISBN: 9780355744262Subjects--Topical Terms:

3168411
Systems science.

Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets.
LDR:04821nmm a2200385 4500 001 2161347
005 20180823122930.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355744262
035 $a (MiAaPQ)AAI10688507
035 $a (MiAaPQ)stevens:10447
035 $a AAI10688507
040 $a MiAaPQ $c MiAaPQ
100 1 $a Alsulaiman, Talal. $3 3349311
245 1 0 $a Behavioral Financial Network: An Agent-Based Approach for the Complexity of Heterogeneous Financial Markets.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 244 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Khaldoun Khashanah.
502 $a Thesis (Ph.D.)--Stevens Institute of Technology, 2017.
520 $a Artificial financial markets (AFMs) aim to investigate the link between individual behaviors and financial market dynamics. The financial market is a complex system in which the relation between its components cannot be captured analytically. Computational approaches, such as simulation, are needed to comprehend this relation. A common method used to build AFMs is the agent-based simulation.
520 $a The primary segments of the AFM are agents (investors), assets, and asset prices. However, we intend to contribute to the AFMs modeling community by providing a model that has its own attributes and properties. We plan to investigate the effects of various conditions on agents' wealth and market's dynamic. The fundamental focus of the research is to incorporate behavioral biases into the trading decisions. In addition, we investigate the effects of network structures and direct interaction.
520 $a The market is divided into two hierarchical levels: the stock market (macrolevel) and the investors (microlevel). At the macrolevel, we display the environment in which the agents (investors) live where the environment may be formed in term of the network topology. In integration, the macrolevel involves the role of regulatory authority. The regulatory authority oversees the market through various tools such as the interest rate and imposed a tax on the transactions. Further, the regulator may set upper limits on holding or short-selling positions.
520 $a At the microlevel, we distinguished between the investors in terms of their trading preferences, behaviors, and investment strategies. The agent may be risk-averse, risk-averse with overconfidence or conservative behaviors or he may be loss-averse with overconfidence or conservative behaviors. The adopted investment strategies in this model are zero intelligence, fundamental, momentum, and adaptive investors who use the artificial neural network (ANNT). The investors in our model have a direct interaction with one other. They impart the market sentiment with the agents in their connectedness bunch. In view of the new information, they settle on their official investment's decision. The agents in the model have adaptive traits where they may switch their investment strategies and behaviors according to the market state.
520 $a A simulation model will produce a time series of stock prices. From this time series, we may find the mean, variance, skewness and kurtosis of the returns. We validate the model by defining the parameters under investigation. The important parameters will be calibrated using a scatter search meta-heuristic algorithm. As soon as the parameters are calibrated, we test the model's outcomes using statistics techniques against the S&P 500 series. However, the validation is limited to fat tails, autocorrelation, and volatility clusters.
520 $a The research covers the flow of information as stochastic processes. The information can be seen as news, broadcast, economic or social events. However, agents' reactions to these pieces of information differed, and the diffusion varied due to the heterogeneic nature of the market. In this research, we mapped the reactions of the news to the agents' behaviors and agents' connectivity to investigate market's dynamic.
520 $a An additional prime contribution is to emphasize the role of financial networks. We model the financial market as a multidimensional network of networks (NoN) within the domain of agent-based models. This is accomplished by combining agents' information connectivity to the agents' the trading strategies and behaviors. A design of network structures that discusses the assortativity concept of Newman is implemented to examine their effect on emergence behaviors of the market.
590 $a School code: 0733.
650 4 $a Systems science. $3 3168411
650 4 $a Finance. $3 542899
650 4 $a Economics. $3 517137
690 $a 0790
690 $a 0508
690 $a 0501
710 2 $a Stevens Institute of Technology. $b Financial Engineering. $3 3181482
773 0 $t Dissertation Abstracts International $g 79-08B(E).
790 $a 0733
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10688507