Decifrando o Mercado de NFTs: A Influência das Conexões de Rede e Transações no Valor de Ativos

Abstract

The market for Non-Fungible Tokens (NFTs) continues to evolve, yet it still lacks robust methodologies to estimate the future value of its assets. Unlike traditional financial markets, NFT pricing is challenged by intangible factors such as the artistic nature of the items and the influence of social and transactional networks among buyers and sellers. This study investigates whether the structural position of participants in the transaction network can serve as a relevant predictor of the future value of NFTs. To this end, we reconstructed the NFT trading network for the period 2020–2021, extracted both structural and transactional metrics of the participants, and applied supervised machine learning models, including deep neural networks. The results demonstrate the feasibility of the proposed approach, achieving 74% accuracy and a global F1-Score of 72%. Interpretability analysis using SHAP values revealed that, in addition to historical price averages, network metrics such as degree and neighborhood significantly contribute to prediction. These findings highlight the role of network dynamics in NFT valuation and point toward promising directions for more transparent and evidence-based pricing methodologies.