Publications

Detailed Information

Prediction of stock price, base rate, and interest rate spread with text data : 텍스트 데이터를 이용한 주식 가격, 기준 금리 및 스프레드 예측

DC Field Value Language
dc.contributor.advisor조성준-
dc.contributor.author김미숙-
dc.date.accessioned2018-05-28T16:11:33Z-
dc.date.available2018-05-28T16:11:33Z-
dc.date.issued2018-02-
dc.identifier.other000000151311-
dc.identifier.urihttps://hdl.handle.net/10371/140592-
dc.description학위논문 (박사)-- 서울대학교 대학원 : 공과대학 산업공학과, 2018. 2. 조성준.-
dc.description.abstractMethodologies in financial research based on a variety of predictions models have been actively developed for the analysis of market behaviors. The significance of prediction modeling in the financial market cannot be emphasized better especially given that it leads directly to large transaction profit. In terms of applicability for the active agents in the market requires, these research results require both predictability and interpretability. In this study, we propose methodologies suitable for incorporating distinct characteristics across different financial data in the analysis for the purpose of effective prediction modeling. Firstly, we propose a methodology that quantitatively and qualitatively predicts the stock price movements through sentiment analysis of corporate disclosures in the stock market. The proposed method predicts stock price movements by embedding the documents, and the class of documents defined to fit the purpose of our study, to the same projection space based on the distributed representations learned, and compares the predictive performance against various existing models. The results provide prime evidence of effectiveness of our prediction results through visualization of document sentiments. In addition, we propose a methodology specifically designed for predicting the vote results of the base interest rate, which is the most important factor in the bond market, developed within the premise of the Korean bond market. Our methodology allows computation of sentence sentiments using the monetary policy decision recorded as text data, which is released before the announcement of the vote result, which are then aggregated to the document level to express the document sentiment of monetary policy decision into values. Using these sentiments, we predict the vote results of the base rate. Finally, we define the framework for predicting the spread, the difference between two bond rates with different maturities. The framework mainly considers the following three aspects as the standards for the effectiveness of research: interpretability, proper prediction metrics, and the reporting methods. The framework use wrapper approaches for the practical interpretation of important variables, while using PARE, in combination with MAE, as prediction metrics, for taking into account the tolerance of the spread. Lately, we suggest various visualizations and hierarchical illustration of significant variables as more applicable and effective reporting methods. This dissertation defines a variety of financial problems, proposes analytical methodologies, compares quantitative prediction power, and provide the qualitative evidence. The proposed methodologies prove to serve as a quick and accurate data-driven decision making support tool to active agents in the real-site.-
dc.description.tableofcontentsChapter 1 Introduction 1
1.1 Financial Markets 1
1.2 Data-driven Decision Making 4
1.3 Outlook of this Dissertation 8
Chapter 2 Literature Review 11
2.1 Financial Predictability Modeling 11
2.2 Financial Interpretability Modeling 14
2.3 Data-driven Modeling Techniques 18
Chapter 3 Prediction of Stock Price through Sentiment Analysis of Corporate Disclosures 34
3.1 Background 34
3.2 Proposed Method 38
3.2.1 Distributed Representation 38
3.2.2 Visualization 42
3.2.3 Model-based Prediction 43
3.3 Experimental Results 45
3.3.1 Data Descriptions 45
3.3.2 Experimental Settings 47
3.3.3 Quantitative Prediction 47
3.3.4 Qualitative Prediction 48
3.4 Summary 53
Chapter 4 Predicting the Korean Monetary Policy Committees Vote Results with Monetary Policy Decision Text 56
4.1 Background 56
4.2 Proposed Method 63
4.2.1 Sentence Representation 63
4.2.2 Prediction Models of Sentence Sentiment 64
4.2.3 Aggregation of Sentence Sentiment 66
4.3 Experimental Results 69
4.3.1 Data Descriptions 69
4.3.2 Sentence Sentiment Prediction of a Monetary Policy Decision 70
4.3.3 Vote Result Prediction 73
4.4 Summary 75
Chapter 5 Modeling the 3-10 Year Spreads with Economic Indicators 78
5.1 Background 78
5.2 Proposed Method 80
5.2.1 Preprocessing 83
5.2.2 Prediction Models 83
5.2.3 Feature Selection 83
5.2.4 Evaluation 85
5.2.5 Reporting 88
5.3 Experimental Results 89
5.3.1 Data Descriptions 89
5.3.2 Experimental Settings 90
5.3.3 Spread Prediction 92
5.4 Summary 94
Chapter 6 Conclusion 97
6.1 Contributions 97
6.2 Future Work 101
Bibliography 102
국문초록 115
-
dc.formatapplication/pdf-
dc.format.extent6272950 bytes-
dc.format.mediumapplication/pdf-
dc.language.isoen-
dc.publisher서울대학교 대학원-
dc.subjectData mining-
dc.subjectMachine learning-
dc.subjectWord embedding-
dc.subjectDistributed representation-
dc.subjectBag-of-words-
dc.subjectSentiment analysis-
dc.subjectStock price predition-
dc.subjectVote result prediction of monetary policy committee-
dc.subjectBond spread prediction-
dc.subjectCorporate disclosures-
dc.subjectMonetary policy documents-
dc.subjectEconomic indicators-
dc.subject.ddc670.42-
dc.titlePrediction of stock price, base rate, and interest rate spread with text data-
dc.title.alternative텍스트 데이터를 이용한 주식 가격, 기준 금리 및 스프레드 예측-
dc.typeThesis-
dc.description.degreeDoctor-
dc.contributor.affiliation공과대학 산업공학과-
dc.date.awarded2018-02-
Appears in Collections:
Files in This Item:

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share