Proximity-Based Payment Authentication Using RSSI and Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing transaction authorization methods at merchant POS terminals require user authentication through PIN or signature input, which is cumbersome and increases network bandwidth, while lacking real-time fraud detection capabilities.

Innovation Solution

Implementing NFC and RFID technology in combination with machine learning to estimate the proximity radius of devices associated with a payment card, using a machine learning model to continuously train and update thresholds for authentication, thereby authorizing or denying transactions based on device proximity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual authentication (PIN or signature input) is used at POS terminals, then user authorization can be obtained, but the operation becomes cumbersome and network bandwidth increases

Engineering Contradiction:

Improveauthorization reliabilityVSAvoidoperation convenience

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent replaces the mechanical interaction of manual PIN entry or signature capture with a wireless electromagnetic field-based authentication system. NFC/RFID tags in payment cards communicate proximity information wirelessly to the POS terminal, eliminating the need for physical keyboard input or signature pad interaction while maintaining authorization reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces NFC/RFID tags as intermediary devices that carry proximity information. These tags act as mediators between the user's physical proximity to the card and the authorization system, translating spatial relationship into authentication data without requiring direct manual input

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If manual authentication methods are used, then user authorization can be verified, but network bandwidth consumption increases

Engineering Contradiction:

Improveauthorization verificationVSAvoidnetwork bandwidth

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The patent extracts the essential authentication information (proximity verification) from the complex manual authentication process. By using NFC/RFID tags to carry proximity data, the system separates the verification function from the communication channel, allowing authorization to be determined locally without transmitting large amounts of data over the network

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent uses lightweight NFC/RFID tags that consume minimal resources. These tags provide the necessary proximity information in a compact, low-bandwidth format, replacing heavy manual authentication protocols with lightweight electromagnetic signals that require minimal network bandwidth

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Productivity

If traditional authentication methods are used, then transactions can be authorized, but real-time fraud detection capabilities are lacking

Engineering Contradiction:

Improvetransaction authorization speedVSAvoidfraud detection capability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements feedback by continuously monitoring NFC/RFID tag proximity data during transactions. The system compares expected proximity patterns against actual measurements in real-time, providing immediate feedback that enables fraud detection without delaying authorization. Deviations from expected proximity relationships trigger fraud alerts while maintaining normal transaction flow

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary fraud detection by analyzing proximity information before completing the authorization. The NFC/RFID system verifies spatial relationships in advance, establishing a baseline of expected device proximity that enables rapid fraud detection during the transaction without adding time to the authorization process

Inventive Principle:

Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enhances transaction authorization with reduced fraud risk by eliminating the need for manual input and optimizing network bandwidth, while providing real-time fraud detection through continuous model training.

Implementation Method 1

pairing a payment card to a mobile electronic device and a wearable device, the payment card including at least one of near-field communication (NFC) or radio frequency identification (RFID) capability

Methodology Applied

Scientific EffectNear-field communication (NFC):

Implementation Method 2

Methodology Applied

Scientific EffectRadio frequency identification (RFID):

Implementation Method 3

training a machine learning model by obtaining first received signal strength indicator (RSSI) data from the payment card, the mobile electronic device, and the wearable device at calibrated distances

Methodology Applied

Scientific EffectReceived signal strength indicator (RSSI):

Data Source

PatentUS20260073380A1Machine learning for authentication based on device proximity

Publication Date: 2026.03.12 MASTERCARD INT INC

AI summary

A device and method of authentication includes pairing a card to a mobile electronic device and a wearable device. A machine learning model is trained by obtaining first received signal strength indicator (RSSI) data from the card, the mobile electronic device, and the wearable device at calibrated distances. A first estimated proximity radius encompassing the card, the mobile electronic device, and the wearable device is calculated. The first estimated proximity radius is classified to be within a threshold. Upon receipt of a request to authorize a request, second RSSI data from the card, the mobile electronic device, and the wearable device is obtained. A second estimated proximity radius encompassing the card, the mobile electronic device, and the wearable device is calculated. Using the trained machine learning model, the second estimated proximity radius is determined to be within the threshold. Authentication is then complete.