Subscription Transaction Detection for Temporary Payment Blocks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often lose track of their subscription services, leading to unintended recurring charges, and existing methods for managing these subscriptions are time-consuming and require direct interaction with merchant customer service.
Innovation Solution
A machine learning model at a financial institution analyzes historical transaction data to identify subscription-type recurring transactions, allowing users to manage these subscriptions through their financial institution's mobile app without direct merchant interaction, including options to cancel, pause, or update services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users manually manage subscriptions through merchant customer service or websites, then subscription management is possible, but it is time-consuming and requires direct interaction with merchants
Solution Approach 1:
The patent introduces a financial institution's processing server as an intermediary between users and merchants. This server receives transaction data from merchants, identifies subscription-type recurring transactions using machine learning models, and provides centralized management capabilities through a mobile app. Users can manage subscriptions through this intermediary without direct merchant interaction, significantly reducing time and effort required for subscription management.
2Measurement precision
If machine learning models are used to identify subscription transactions, then automated detection accuracy is improved, but computational resources and processing time are increased
Solution Approach 1:
The patent implements machine learning models that are pre-trained offline on historical transaction data to recognize subscription patterns. During actual transaction processing, the pre-trained models quickly evaluate new transactions against learned patterns, enabling accurate identification of subscription-type transactions with minimal real-time computational overhead. This preliminary training approach separates the computationally intensive learning phase from the efficient inference phase.
3Adaptability or versatility
If centralized subscription management through financial institution is implemented, then user control over subscriptions is improved, but system complexity is increased
Solution Approach 1:
The patent creates a universal subscription management system through the financial institution's processing server that handles multiple functions: transaction data reception from various merchants, machine learning-based subscription identification, user interface provision through mobile app, and centralized control operations. This multi-functional system allows users to manage diverse subscriptions from different merchants through a single interface, increasing adaptability without requiring users to interact with multiple merchant systems.
Data Source
AI summary
Systems, methods, and apparatuses for blocking subscription transactions for a given subscription from being applied to an electronic payment method, while allowing other transactions to be applied to the electronic payment method. Aspects further comprise training a machine learning model, based on historical transaction data, to predict subscription transactions, and updating the machine learning model based on incoming transactions. Aspects further provide for allowing a user to indicate they wish to cancel a subscription, blocking charges to the subscription while communicating with the merchant to cancel the subscription, and then removing the block after the subscription is confirmed canceled. to Aspects further provide for detecting when a subscription transaction was not blocked properly and updating the machine learning model to block similar subscription transactions in the future.