Skip to main content

An empirical data mining study on Non-fungible Token (NFT) markets

Resource type
Thesis type
(Thesis) M.Sc.
Date created
2023-08-16
Authors/Contributors
Abstract
Non-fungible tokens (NFTs) have garnered significant attention as a unique asset class, but comprehending their pricing and making well-informed investment choices remains challenging. To tackle this challenge, we conducted an extensive data mining analysis of the NFT markets, examining transaction frequency, category preferences, price distributions, and inequality. Employing hierarchical clustering, we organized NFTs into distinct clusters based on their sales history and price dynamics. We developed predictive models for estimating NFT prices, utilizing linear regression, regularization techniques, and the Multi-Layer Perceptron (MLP) model. This research yields valuable insights into the NFT markets, empowering investors and artists to make informed decisions. Furthermore, it contributes to the broader field of digital assets, promoting market fairness and transparency. By comprehending the factors influencing NFT prices and organizing NFTs into clusters, this study enhances transparency and facilitates equitable valuation.
Document
Extent
68 pages.
Identifier
etd22623
Copyright statement
Copyright is held by the author(s).
Permissions
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Supervisor or Senior Supervisor
Thesis advisor: Pei, Jian
Language
English
Member of collection
Download file Size
etd22623.pdf 2.58 MB

Views & downloads - as of June 2023

Views: 64
Downloads: 11