Predictive Modeling of NFT Adoption for Enhancing FinTech Applications in Iran’s Banking Sector

This research proposes a data-driven modeling framework for the expansion of financial technology (FinTech) in Iran’s banking system through the integration of non-fungible tokens (NFTs). Using a data-mining approach, the study analyzes behavioral data collected from customers of Iranian cryptocurrency exchanges from ۲۰۲۰ to ۲۰۲۵. After preprocessing, the dataset was evaluated with decision trees, Naïve Bayes, neural networks, and rough set algorithms. The results demonstrate that the rough set model achieved the highest predictive accuracy (۰.۹۸) in identifying user behavior patterns and the principal factors influencing NFT adoption.From a banking and policy-making perspective, the findings highlight the potential of NFT-enabled FinTech platforms to offer innovative tools for digital asset management, enhance transparency, reduce transaction costs, and promote financial inclusion. At the same time, risks such as regulatory uncertainty, cyber fraud, and price volatility emphasize the urgent need for tailored supervisory and governance frameworks that are suited to Iran’s economic environment.The originality of this study lies in offering a quantitative and simulation-oriented model that bridges theoretical insights with practical applications. By doing so, it provides actionable guidance for the Central Bank of Iran, financial institutions, and regulators to strengthen the digital financial ecosystem and advance the transition toward smart banking.

کلیدواژه ها:

Fintech ، NFT ، Data Mining ، Smart Banking ، Blockchain