Multi-Party Transaction Decisioning for Shared Expense Delegation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack the ability to proactively identify, detect, and manage multi-party transactions, leading to time-consuming and error-prone manual processes for settling shared expenses, and fail to link received payments with original transactions.
Innovation Solution
A system that uses machine learning to identify atypical transactions, accesses user data to determine associated parties, and manages payment delegation and linking, leveraging a multi-party transaction decisioning device, database, user computing devices, and payment processing systems to automate the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual processes are used to identify and settle multi-party transactions, then users can manage shared expenses, but the process becomes time-consuming and error-prone
Solution Approach 1:
The system automatically identifies multi-party transactions and determines payment delegations without requiring manual user intervention. The financial institution's system proactively detects transactions, identifies potential multi-party scenarios using machine learning models, and manages the settlement process autonomously, freeing users from time-consuming manual tracking and calculation.
Solution Approach 2:
The patent replaces manual mechanical processes (users manually tracking, calculating, and collecting payments) with an automated electronic system. Machine learning models analyze transaction data to identify multi-party transactions, and the system automatically manages payment delegations, substituting human effort with intelligent automated processing.
2Extent of automation
If existing rudimentary systems are used to track shared expenses, then some transaction sharing is possible, but the systems fail to proactively identify and detect multi-party transactions
Solution Approach 1:
The system establishes feedback loops where transaction data is continuously analyzed, machine learning models are trained on identified multi-party transactions, and the system learns from user confirmations and corrections. This feedback mechanism improves the accuracy of automatic identification over time and ensures proper linking of payments to original transactions through continuous validation.
Solution Approach 2:
The system performs preliminary analysis of transactions as they occur, using machine learning models to predict and identify multi-party transactions before settlement is complete. By proactively detecting potential multi-party scenarios early in the transaction process, the system can prepare payment delegation structures and maintain accurate links between payments and original transactions in advance.
Data Source
AI summary
Methods, systems, devices, and computer-readable media for a multi-party transaction decisioning system are provided. The system may analyze a purchase transaction associated with a first user and may identify that the transaction is associated with more than one party based on determining that an amount of the transaction is atypical for the first user. The system may identify a party associated with the multi-party transaction based on analyzing data associated with the first user. The system may generate a delegation request for a portion of the amount of the multi-party transaction to be delegated to the identified party and may transmit the delegation request to the identified party. Subsequently, the system may receive a payment transaction from the identified party, and the system may identify that the payment transaction is associated with the previously transmitted delegation request.