Deep learning based text regression

Simple item page
dc.contributorGraduate Program in Systems and Control Engineering.
dc.contributor.advisorSaraçlar, Murat.
dc.contributor.authorDereli, Neşat.
dc.date.accessioned2023-03-16T11:34:58Z
dc.date.available2023-03-16T11:34:58Z
dc.date.issued2019.
dc.description.abstractMost financial analysis methods and portfolio management techniques are based on risk classification and risk prediction. Stock return volatility is a solid indicator of the financial risk of a company. Therefore, forecasting stock return volatility success fully creates an invaluable advantage in financial analysis and portfolio management. While most of the studies are focusing on historical data and financial statements when predicting financial volatility of a company, some studies introduce new fields of information by analyzing soft information which is embedded in textual sources. Fore casting financial volatility of a publicly-traded company from its annual reports has been previously defined as a text regression problem. Recent studies use a manually labeled lexicon to filter the annual reports by keeping sentiment words only. In or der to remove the lexicon dependency without decreasing the performance, we replace bag-of-words model word features by word embedding vectors. Using word vectors increases the number of parameters. Considering the increase in number of parame ters and excessive lengths of annual reports, a convolutional neural network model is proposed and transfer learning is applied. Experimental results show that the convolu tional neural network model provides more accurate volatility predictions than lexicon based models.
dc.format.extent30 cm.
dc.format.pagesxiii, 57 leaves ;
dc.identifier.otherSCO 2019 D47
dc.identifier.urihttps://digitalarchive.library.bogazici.edu.tr/handle/123456789/15674
dc.publisherThesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019.
dc.subject.lcshMachine learning.
dc.subject.lcshComputer algorithms.
dc.titleDeep learning based text regression

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
b2034183.033855.001.PDF
Size:
818.37 KB
Format:
Adobe Portable Document Format
Download

Collections

M.S. Theses