Transaction Data Segmentation for Advertising Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to effectively analyze and utilize transaction data from payment cards to provide personalized and targeted advertisements, failing to optimize advertisement campaigns and accurately measure their return on investment.
Innovation Solution
A system that processes transaction data to generate aggregated spending profiles, correlates advertisements with purchases, and uses this information to deliver personalized ads, optimize campaigns, and measure ROI by integrating transaction data with account, merchant, search, social networking, and web data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If transaction data is processed to generate aggregated spending profiles and correlate advertisements with purchases, then advertising effectiveness and ROI measurement are improved, but system complexity and data processing requirements increase
Solution Approach 1:
The system segments transaction data into aggregated spending profiles that categorize consumer behavior patterns. By dividing the vast transaction data into manageable profile segments, the system can effectively analyze and correlate advertising exposure with purchase behavior without being overwhelmed by raw data volume, thus improving advertising effectiveness while maintaining manageable system complexity
Solution Approach 2:
The patent introduces an intermediary correlation layer that connects advertisement exposure data with transaction data through spending profiles. This intermediary mechanism facilitates the measurement of advertising ROI by acting as a bridge between marketing campaigns and consumer purchases, improving reliability of effectiveness measurement while structuring the complexity into distinct processing layers
2Productivity
If personalized advertisements are delivered based on spending patterns, then customer engagement increases, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-generating aggregated spending profiles from transaction data before advertising campaigns are launched. These profiles capture consumer spending patterns and preferences in advance, enabling rapid delivery of personalized advertisements without requiring real-time analysis during campaign execution, thus improving customer engagement while reducing data processing time
Solution Approach 2:
The system dynamically adjusts advertisement personalization based on updated spending patterns while maintaining efficiency. By implementing dynamic profile updates and correlation mechanisms that adapt to changing consumer behavior without complete reprocessing, the system sustains high customer engagement levels while optimizing computational resource usage over time
Data Source
AI summary
In one aspect, a system includes a transaction handler to process transactions, a data warehouse to store data recording the transactions, and at least one processor coupled with the data warehouse and configured to identify a first set of customers who made first transactions correlated with an advertisement, identify a second set of customers not in the first set of customers, and determine a difference between a first pattern in a first set of transactions of the first set of customers and a second pattern in a second set of transactions of the second set of customers.