Automated theme search in ICO whitepapers
Publication Type
Journal Article
Publication Date
11-2019
Abstract
The authors explore how topic modeling can be used to automate the categorization of initial coin offerings (ICOs) into different topics (e.g., finance, media, information, professional services, health and social, natural resources) based solely on the content within the whitepapers. This tool has been developed by fitting a latent Dirichlet allocation (LDA) model to the text extracted from the ICO whitepapers. After evaluating the automated categorization of whitepapers using statistical and human judgment methods, it is determined that there is enough evidence to conclude that the LDA model appropriately categorizes the ICO whitepapers. The results from a two-population proportion test show a statistically significant difference between topics in the success of an ICO being funded, indicating that the topics are usefully differentiated and suggesting that the topic model could be used to help predict whether an ICO will be successful.
Keywords
Statistical methods, simulations, big data/machine learning, cryptocurrency, ICO
Discipline
Databases and Information Systems | Finance and Financial Management
Research Areas
Information Systems and Management
Publication
Journal of Finance and Data Science
Volume
1
Issue
4
First Page
140
Last Page
158
ISSN
2405-9188
Identifier
10.3905/jfds.2019.1.011
Publisher
Pageant Media
Citation
FU, Chuanjie; KOH, Andrew; and GRIFFIN, Paul Robert.
Automated theme search in ICO whitepapers. (2019). Journal of Finance and Data Science. 1, (4), 140-158.
Available at: https://ink.library.smu.edu.sg/sis_research/4720
Additional URL
https://doi.org/10.3905/jfds.2019.1.011