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

Application of Deep Learning to Corporate Credit Rating.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Application of Deep Learning to Corporate Credit Rating./
作者:	Wang, Dan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	117 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-07, Section: B.
Contained By:	Dissertations Abstracts International83-07B.
標題:	Finance. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28774347
ISBN:	9798762192545

Application of Deep Learning to Corporate Credit Rating.
Wang, Dan.

Application of Deep Learning to Corporate Credit Rating. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 117 p.

Source: Dissertations Abstracts International, Volume: 83-07, Section: B.

Thesis (Ph.D.)--Stevens Institute of Technology, 2021.

This item must not be sold to any third party vendors.

Corporate credit rating is an assessment of the credit risk level of a company, it helps investors with their investment decision making and facilitates the process of companies raising money from the capital market. Therefore, understanding the nature of the credit rating process and better assessing credit rating is important for both investors and companies. In this thesis, we first analyze the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating. The goal of this analysis is to provide recommendations for credit assessment using deep learning algorithms. We then investigate encoding techniques to transform 1D data into 2D images. Specifically, we analyze the performance of three encoding methods (Sequential Arrangement, Category Chunk Arrangement, and Hilbert Vector Arrangement) applied to fundamental data and financial ratio data. The goal of the encoding method is to investigate whether arranging input data using 2D encoding techniques is beneficial to the credit rating assessment problem. Finally, we propose a new "sparsity algorithm" which provides a simple suggestion to publicly traded companies to improve their credit ratings. Our study provides recommendations about a "best" architecture to assess corporate credit rating with respect to feature selection, data splitting, and input feature arrangement to researchers and investors. The suggestions from our sparsity algorithm are validated by synthetically generated datasets and quarterly financial statements from companies in the financial, healthcare, and IT sectors.

ISBN: 9798762192545Subjects--Topical Terms:

542899
Finance.
Subjects--Index Terms:

Corporate Credit Rating

Application of Deep Learning to Corporate Credit Rating.
LDR:02725nmm a2200349 4500 001 2352804
005 20221205085609.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798762192545
035 $a (MiAaPQ)AAI28774347
035 $a AAI28774347
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Dan. $3 1275311
245 1 0 $a Application of Deep Learning to Corporate Credit Rating.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 117 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-07, Section: B.
500 $a Advisor: Florescu, Ionut IF.
502 $a Thesis (Ph.D.)--Stevens Institute of Technology, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Corporate credit rating is an assessment of the credit risk level of a company, it helps investors with their investment decision making and facilitates the process of companies raising money from the capital market. Therefore, understanding the nature of the credit rating process and better assessing credit rating is important for both investors and companies. In this thesis, we first analyze the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating. The goal of this analysis is to provide recommendations for credit assessment using deep learning algorithms. We then investigate encoding techniques to transform 1D data into 2D images. Specifically, we analyze the performance of three encoding methods (Sequential Arrangement, Category Chunk Arrangement, and Hilbert Vector Arrangement) applied to fundamental data and financial ratio data. The goal of the encoding method is to investigate whether arranging input data using 2D encoding techniques is beneficial to the credit rating assessment problem. Finally, we propose a new "sparsity algorithm" which provides a simple suggestion to publicly traded companies to improve their credit ratings. Our study provides recommendations about a "best" architecture to assess corporate credit rating with respect to feature selection, data splitting, and input feature arrangement to researchers and investors. The suggestions from our sparsity algorithm are validated by synthetically generated datasets and quarterly financial statements from companies in the financial, healthcare, and IT sectors.
590 $a School code: 0733.
650 4 $a Finance. $3 542899
650 4 $a Statistics. $3 517247
653 $a Corporate Credit Rating
653 $a Counterfactual Explanation
653 $a Deep Learning
653 $a Encoding method
690 $a 0508
690 $a 0463
710 2 $a Stevens Institute of Technology. $b School of Business. $3 3428368
773 0 $t Dissertations Abstracts International $g 83-07B.
790 $a 0733
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28774347