Publications-Proceedings

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

TitleOn the Construction and Analysis of Financial Time-Series-Oriented Lexicons
CreatorLai, Chen-Yi;Wang, Chuan-Ju;Tsai, Ming-Feng
蔡銘峰
Contributor資科系
Date2015
Date Issued22-Jun-2016 17:14:44 (UTC+8)
SummaryThis paper proposes a novel framework to build a time-series-oriented lexicon which can cover di erent types of sources and also has explicit links with the targets of prediction problems. In the framework, the input is composed of a text stream, such as nancial news and a nancial time series, such as the stock prices of a company. We then calculate the Pearson correlation between the frequency series of each word and the stock price series of a company. Although Pearson correlation gives a good idea of how much the two time series are correlated, it has a limitation in capturing the similarity when one of the series is stretched or shifted. To overcome this limitation, we adopt Dynamic time warping (DTW) to handle the problem. Finally, the words with high correlations will be extracted to build the time-series-oriented lexicon.
RelationProceedings of the 35th International Symposium on Forecasting (ISF `15), 2015
Typeconference
dc.contributor 資科系
dc.creator (作者) Lai, Chen-Yi;Wang, Chuan-Ju;Tsai, Ming-Feng
dc.creator (作者) 蔡銘峰zh_TW
dc.date (日期) 2015
dc.date.accessioned 22-Jun-2016 17:14:44 (UTC+8)-
dc.date.available 22-Jun-2016 17:14:44 (UTC+8)-
dc.date.issued (上傳時間) 22-Jun-2016 17:14:44 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/98235-
dc.description.abstract (摘要) This paper proposes a novel framework to build a time-series-oriented lexicon which can cover di erent types of sources and also has explicit links with the targets of prediction problems. In the framework, the input is composed of a text stream, such as nancial news and a nancial time series, such as the stock prices of a company. We then calculate the Pearson correlation between the frequency series of each word and the stock price series of a company. Although Pearson correlation gives a good idea of how much the two time series are correlated, it has a limitation in capturing the similarity when one of the series is stretched or shifted. To overcome this limitation, we adopt Dynamic time warping (DTW) to handle the problem. Finally, the words with high correlations will be extracted to build the time-series-oriented lexicon.
dc.format.extent 1563922 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Proceedings of the 35th International Symposium on Forecasting (ISF `15), 2015
dc.title (題名) On the Construction and Analysis of Financial Time-Series-Oriented Lexicons
dc.type (資料類型) conference