Corporate Delisting Prediction via Deep Learning Algorithms

碩士 === 臺北市立大學 === 資訊科學系 === 104 === This thesis provides a new perspective on the corporate delisting prediction problem using deep learning algorithms. By taking the advantages of deep learning, the representable factors of input data will no longer need to be explicitly extracted, but can be impli...

Full description

Bibliographic Details
Main Authors:	Yeh, Shu-Hao, 葉書豪
Other Authors:	Wang, Chuang-Ju
Format:	Others
Language:	en_US
Published:	2016
Online Access:	http://ndltd.ncl.edu.tw/handle/97318466476221740363

id	ndltd-TW-104UT005394019
record_format	oai_dc
spelling	ndltd-TW-104UT0053940192017-09-24T04:40:57Z http://ndltd.ncl.edu.tw/handle/97318466476221740363 Corporate Delisting Prediction via Deep Learning Algorithms 利用深度學習演算法預測企業下市模式 Yeh, Shu-Hao 葉書豪碩士臺北市立大學資訊科學系 104 This thesis provides a new perspective on the corporate delisting prediction problem using deep learning algorithms. By taking the advantages of deep learning, the representable factors of input data will no longer need to be explicitly extracted, but can be implicitly learned by the deep learning algorithms. We consider the stock returns of both delisting and listing companies as input signals and adopt two of the deep learning architectures, Deep Belief Networks (DBN) and Convolutional Neural Networks (CNN), to train the prediction models. The experimental results show that the proposed approach outperforms traditional machine learning algorithms. Wang, Chuang-Ju 王釧茹 2016 學位論文 ; thesis 31 en_US
collection	NDLTD
language	en_US
format	Others
sources	NDLTD
description	碩士 === 臺北市立大學 === 資訊科學系 === 104 === This thesis provides a new perspective on the corporate delisting prediction problem using deep learning algorithms. By taking the advantages of deep learning, the representable factors of input data will no longer need to be explicitly extracted, but can be implicitly learned by the deep learning algorithms. We consider the stock returns of both delisting and listing companies as input signals and adopt two of the deep learning architectures, Deep Belief Networks (DBN) and Convolutional Neural Networks (CNN), to train the prediction models. The experimental results show that the proposed approach outperforms traditional machine learning algorithms.
author2	Wang, Chuang-Ju
author_facet	Wang, Chuang-Ju Yeh, Shu-Hao 葉書豪
author	Yeh, Shu-Hao 葉書豪
spellingShingle	Yeh, Shu-Hao 葉書豪 Corporate Delisting Prediction via Deep Learning Algorithms
author_sort	Yeh, Shu-Hao
title	Corporate Delisting Prediction via Deep Learning Algorithms
title_short	Corporate Delisting Prediction via Deep Learning Algorithms
title_full	Corporate Delisting Prediction via Deep Learning Algorithms
title_fullStr	Corporate Delisting Prediction via Deep Learning Algorithms
title_full_unstemmed	Corporate Delisting Prediction via Deep Learning Algorithms
title_sort	corporate delisting prediction via deep learning algorithms
publishDate	2016
url	http://ndltd.ncl.edu.tw/handle/97318466476221740363
work_keys_str_mv	AT yehshuhao corporatedelistingpredictionviadeeplearningalgorithms AT yèshūháo corporatedelistingpredictionviadeeplearningalgorithms AT yehshuhao lìyòngshēndùxuéxíyǎnsuànfǎyùcèqǐyèxiàshìmóshì AT yèshūháo lìyòngshēndùxuéxíyǎnsuànfǎyùcèqǐyèxiàshìmóshì
_version_	1718540391291027456

Corporate Delisting Prediction via Deep Learning Algorithms

Similar Items