Dominant Account Profile Classification for Payment Transactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial institutions and merchants face challenges in accurately determining the merchant category code (MCC) alignment for customer payment transactions, leading to ineffective offers and wastage of network and processing resources.
Innovation Solution
A method and system for determining a dominant account profile by generating a classification model based on transaction data, predicting scores for various MCCs, and recommending the most likely transaction categories, thereby optimizing offer communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If financial institutions communicate offers to customers based on traditional MCC classification methods, then offers are sent to encourage payment transactions, but the offers are ineffective and network resources are wasted
Solution Approach 1:
The system changes the parameters used for customer classification from traditional MCC-based static classification to dynamic classification based on multiple transaction attributes including transaction amount, frequency, time patterns, and merchant categories. This enables more accurate prediction of customer behavior and improves offer effectiveness while reducing resource wastage by targeting only relevant customers.
Solution Approach 2:
The system performs preliminary analysis of transaction data to generate predicted dominant MCCs and customer profiles before communicating offers. By pre-processing transaction data and identifying likely transaction categories in advance, the system can target offers more effectively and avoid wasting resources on customers unlikely to respond.
2Measurement precision
If financial institutions use traditional MCC assignment methods, then merchant categories are assigned based on initial classification, but accurate determination of customer transaction alignment is unable to be achieved
Solution Approach 1:
The system segments the classification process into multiple components: transaction data collection, pattern recognition, dominant MCC prediction, and profile generation. By dividing the complex classification task into manageable segments, the system achieves higher accuracy in determining customer-MCC alignment while making the overall system more tractable and implementable.
Solution Approach 2:
The system introduces an intermediary classification model that acts as a mediator between raw transaction data and final MCC assignment. This intermediate layer processes transaction patterns and predicts dominant MCCs, improving measurement precision while isolating the complexity within the model rather than requiring complex changes throughout the entire system.
3Productivity
If financial institutions communicate a large number of offers to customers, then more customers may be reached, but network resources and processing resources are wasted
Solution Approach 1:
The system applies partial action by communicating offers only to customers for whom the predicted dominant MCC aligns with the offer category, rather than broadcasting to all customers. This selective approach maintains productivity by reaching the right customers while avoiding excessive resource consumption on unlikely respondents.
Solution Approach 2:
The system uses feedback from transaction data to continuously refine customer profiles and predict dominant MCCs. By incorporating feedback mechanisms that learn from actual customer behavior, the system improves its ability to identify responsive customers, thereby maintaining high reach effectiveness while reducing resource wastage on non-responsive segments.
Data Source
AI summary
Provided is a computer-implemented method for determining a dominant account profile of an account. The method may include receiving transaction data associated with a plurality of payment transactions conducted within a predetermined time interval of activation of an account involved in the plurality of payment transactions, generating a dominant account profile classification model, determining a plurality of prediction scores for the account based on the dominant account profile classification model and the transaction data, where determining the plurality of prediction scores includes determining, for the user, a prediction score for each dominant account profile, where a prediction score includes a prediction of whether the user will conduct a threshold value of payment transactions using the account in one or more payment transaction categories of a plurality of payment transaction categories, and communicating data associated with the plurality of prediction scores.