Predictors of NFT Prices: An Automated Machine Learning Approach

Ilan Alon, Vanessa P.G. Bretas, Villi Katrih

Research output: Contribution to journalArticlepeer-review

4 Scopus citations


This article aims to broaden the understanding of the non-fungible tokens (NFTs) pricing determinants by investigating features, both market- and network-related aspects. NFTs are uniquely identifiable digital assets stored on the blockchain. Ownership is assigned through smart contracts and can be transferred or resold by the owner. The authors analyzed a comprehensive dataset from with over 19,183 datapoints on NFT prices and NFT social communities using automated machine learning (AML), a suitable technique to investigate the most impactful factors due to a lack of knowledge on the exact determinants. Findings show that network factors are the most important pricing determinants: Twitter members followed by Discord members. Online communities drive the price of NFTs, but not in a linear fashion. Given the newness of the phenomenon and no agreed upon pricing models, this article contributes by using AML to discover the most relevant determinants of non-fungible tokens (NFT) prices.

Original languageEnglish
JournalJournal of Global Information Management
Issue number1
StatePublished - 2023


  • AML
  • Artificial Intelligence
  • Digital Assets
  • NFTs
  • Non-fungible Tokens
  • Pricing
  • Social Metrics


Dive into the research topics of 'Predictors of NFT Prices: An Automated Machine Learning Approach'. Together they form a unique fingerprint.

Cite this