Abstract
This disclosure describes a system and method for predicting a user's intended Near Field Communication (NFC) use case before a complete NFC transaction occurs. Unlike existing reactive NFC systems that rely on Application ID (AID) acquisition during a transaction, this system leverages machine learning (ML) models trained with diverse contextual data to anticipate the AID and further disambiguate between multiple use cases or applications for the same AID. This pre-transaction prediction enhances user experience and efficiency by reducing friction, saving time, reducing risk of accidental payments, and enabling seamless and intuitive NFC interactions, such as automatically presenting the correct pass or initiating an action without manual selection. The system can operate in the cloud, on-device for enhanced privacy and customization, or in a combination of both approaches.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Rahmati, Ahmad; Pius, Roshan; and Tuli, Amol, "ML-based pre-transaction NFC application prediction", Technical Disclosure Commons, (December 22, 2025)
https://www.tdcommons.org/dpubs_series/9067