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

FindBook

Google Book

Amazon

博客來

Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks : = A Stochastic and Deep Learning Approach.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks :/
其他題名:	A Stochastic and Deep Learning Approach.
作者:	Zrida, Marwen.
面頁冊數:	1 online resource (144 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-04, Section: A.
Contained By:	Dissertations Abstracts International84-04A.
標題:	Neural networks. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29342803click for full text (PQDT)
ISBN:	9798351491073

Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks : = A Stochastic and Deep Learning Approach.
Zrida, Marwen.

Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks :A Stochastic and Deep Learning Approach. - 1 online resource (144 pages)

Source: Dissertations Abstracts International, Volume: 84-04, Section: A.

Thesis (Ph.D.)--North Carolina State University, 2022.

Includes bibliographical references

This research document addresses issues relating to some current optimal portfolio problems. Portfolio management under illiquidity and contagion default loop models are discussed separately and analyzed before modeling the combined risks model. Mono-risk and multi-risk model results will be presented and compared to establish the relevance and need for modeling multiple risk factors at the same time. The optimal portfolio problems will be modeled and solved using deep learning algorithms, which were proven powerful in successfully reaching near optimal investment strategies and, more importantly, overcoming the curse of dimensionality. The presence of risk factors, modeled by jump diffusion processes, will instigate a discussion about the additional mathematical features that need to be included in the corresponding neural networks.To improve the robustness of our portfolio model, this research project will also explore alternative asset pricing techniques. Specifically, we will assess the Brownian motion assumption and will construct two machine learning models that predict illiquid and liquid asset prices using current datasets. We train a classifier to predict daily price movements of NASDAQ, DOW, and S&P 500 using daily financial/political news, presidents' tweets, and recent historical data. We also construct a ML model that predicts House Price Index for different US cities using historical data. These machine learning models will be used, alongside Brownian motion processes, to construct a comprehensive investment algorithm that determines optimal investment strategies under market risks and that helps investors acquire the "right" liquid and illiquid assets.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798351491073Subjects--Topical Terms:

677449
Neural networks.
Index Terms--Genre/Form:

542853
Electronic books.

Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks : = A Stochastic and Deep Learning Approach.
LDR:03029nmm a2200349K 4500 001 2361806
005 20231027102318.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798351491073
035 $a (MiAaPQ)AAI29342803
035 $a (MiAaPQ)NCState_Univ18402039701
035 $a AAI29342803
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Zrida, Marwen. $3 3702490
245 1 0 $a Portfolio Management and Asset Pricing Amid Contagion and Illiquidity Risks : $b A Stochastic and Deep Learning Approach.
264 0 $c 2022
300 $a 1 online resource (144 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-04, Section: A.
500 $a Advisor: Medhin, Negash G. ;Papanicolaou, Andrew.
502 $a Thesis (Ph.D.)--North Carolina State University, 2022.
504 $a Includes bibliographical references
520 $a This research document addresses issues relating to some current optimal portfolio problems. Portfolio management under illiquidity and contagion default loop models are discussed separately and analyzed before modeling the combined risks model. Mono-risk and multi-risk model results will be presented and compared to establish the relevance and need for modeling multiple risk factors at the same time. The optimal portfolio problems will be modeled and solved using deep learning algorithms, which were proven powerful in successfully reaching near optimal investment strategies and, more importantly, overcoming the curse of dimensionality. The presence of risk factors, modeled by jump diffusion processes, will instigate a discussion about the additional mathematical features that need to be included in the corresponding neural networks.To improve the robustness of our portfolio model, this research project will also explore alternative asset pricing techniques. Specifically, we will assess the Brownian motion assumption and will construct two machine learning models that predict illiquid and liquid asset prices using current datasets. We train a classifier to predict daily price movements of NASDAQ, DOW, and S&P 500 using daily financial/political news, presidents' tweets, and recent historical data. We also construct a ML model that predicts House Price Index for different US cities using historical data. These machine learning models will be used, alongside Brownian motion processes, to construct a comprehensive investment algorithm that determines optimal investment strategies under market risks and that helps investors acquire the "right" liquid and illiquid assets.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Neural networks. $3 677449
650 4 $a Finance. $3 542899
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0501
690 $a 0508
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a North Carolina State University. $3 1018772
773 0 $t Dissertations Abstracts International $g 84-04A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29342803 $z click for full text (PQDT)