Publications
Detailed Information
Pricing Subscription Services with Text Data using Hedonic Pricing and Machine Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 박상욱 | - |
dc.contributor.author | Jo Min hwa | - |
dc.date.accessioned | 2023-06-29T01:47:10Z | - |
dc.date.available | 2023-06-29T01:47:10Z | - |
dc.date.issued | 2023 | - |
dc.identifier.other | 000000176304 | - |
dc.identifier.uri | https://hdl.handle.net/10371/192983 | - |
dc.identifier.uri | https://dcollection.snu.ac.kr/common/orgView/000000176304 | ko_KR |
dc.description.abstract | Subscription e-commerce market has grown by more than 100 percent a year over the past five years and the importance of study on subscription services is self-evident nowadays. However, prices in subscription services usually have unclear structures even though offering a reasonable price is one of the most important elements of customer relationship management in service area. Thus, the aim of the study is to consider attributes based on customer preferences obtained by user-generated data and predict price for subscription services more objectively in a way that customers accept it reasonable.
Target data are 10,000 web scraped reviews from representative subscription services of video streaming service brands. Using machine learning techniques, topic modeling, vector space model, dimensionality shrinkage and deriving the value of attributes were done, and hedonic pricing model was defined. In this process, the result shows that a highly predictive value can be obtained by considering the covariance between each value through Partial Least Squares regression that enables supervised Latent Dirichlet Allocation when pricing services with text-based data. Moreover, regarding the result of Netflix, Amazon Prime Video, and HBO Max being overpriced, Disney+, and Hulu being underpriced, this paper presented insights and implications for each service through considering the relationships between price and attributes that customers value and other situations that the services face. | - |
dc.description.tableofcontents | Chapter 1. Introduction 1
Chapter 2. Literature Review 3 2.1. Hedonic Pricing 3 2.2. Pricing Subscription Services 5 2.3. Hedonic Pricing on Subscription Services 7 2.4. Data Mining through Machine Learning 7 2.5. Research questions and organized table of literatures 9 Chapter 3. Development Process and Methodologies 11 3.1. Hedonic Pricing Model 13 3.2. Data Collection & Preprocessing 14 3.2.1. Data 14 3.2.2. Data scraping & Preprocessing 15 3.2.3. LDA, TF-IDF 16 3.2.4. Obtain regression model by PLS (Supervised LDA) 19 3.2.5. Define values of attributes & Hedonic regression model 22 Chapter 4. Application 23 4.1. Pricing each OTT service with LDA and PLS 23 4.2. Results and Implications 27 4.2.1. Implications regarding customer review-based pricing 29 4.2.2. Insights from the prices and attributes carried out from the process of pricing 5 OTT subscription services 30 4.2.3. Implications regarding methodologies 32 Chapter 5. Conclusion 33 Bibliography 35 Appendicies 40 Appendix A 40 Appendix B 41 Appendix C 42 Appendix D 43 Abstract in Korean 44 | - |
dc.format.extent | 44 | - |
dc.language.iso | eng | - |
dc.publisher | Seoul National University | - |
dc.subject | Pricing | - |
dc.subject | Subscription Services | - |
dc.subject | Machine Learning | - |
dc.subject | Latent Dirichlet Allocation | - |
dc.subject | Partial Least Squares | - |
dc.subject | Hedonic Pricing Model | - |
dc.subject.ddc | 658 | - |
dc.title | Pricing Subscription Services with Text Data using Hedonic Pricing and Machine Learning | - |
dc.type | Thesis | - |
dc.type | Dissertation | - |
dc.contributor.AlternativeAuthor | Jo, Min-hwa | - |
dc.contributor.department | Graduate School of Business | - |
dc.description.degree | master | - |
dc.date.awarded | 2023-02 | - |
dc.contributor.major | Operations Management | - |
dc.identifier.uci | I804:11032-000000176304 | - |
dc.identifier.holdings | 000000000049▲000000000056▲000000176304▲ | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.