Spending Wallet Modeling Using Intermediary Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack accuracy in estimating individual and corporate consumer spending behavior due to limited access to comprehensive financial data, making it difficult for financial institutions to target potential customers effectively and manage risk in transactions.
Innovation Solution
A method and apparatus that model consumer or business spending patterns using tradeline data, credit bureau data, and financial statement data to determine the size and share of wallet, excluding balance transfers and providing more accurate spending calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive financial data is accessed to improve spending behavior estimation accuracy, then measurement precision improves, but device complexity and data access difficulty increase
Solution Approach 1:
The patent uses credit bureau data and tradeline data as intermediary sources to obtain comprehensive financial information without directly accessing all underlying financial institutions' proprietary systems. These intermediaries aggregate and standardize data from multiple sources, reducing the complexity of direct comprehensive data access while maintaining measurement precision.
Solution Approach 2:
The patent segments the comprehensive financial data into specific components: credit bureau data, tradeline data, and financial statement data. This segmentation allows the system to access and process specific data types from appropriate sources independently, reducing overall system complexity while achieving accurate spending behavior estimation through multiple data dimensions.
2Measurement precision
If multiple data sources are integrated to improve customer profiling accuracy, then measurement precision improves, but loss of information and data integration difficulty increase
Solution Approach 1:
The patent creates a universal data model that processes multiple data types (credit bureau data, tradeline data, financial statement data) through a common framework. This multi-functional approach ensures consistent processing and integration of diverse data sources, maintaining information integrity while achieving comprehensive customer profiling accuracy.
Solution Approach 2:
The system incorporates feedback mechanisms where spending behavior estimates are continuously refined by comparing model predictions with actual spending patterns from multiple data sources. This feedback loop reduces information loss by validating and adjusting data integration against observed behavior, improving customer profiling accuracy over time.
3Ease of operation
If traditional credit scoring methods are used to simplify risk assessment, then ease of operation improves, but measurement precision of spending capacity deteriorates
Solution Approach 1:
The patent transforms traditional credit scoring parameters by incorporating additional data dimensions (tradeline data, financial statement data) and changing the parameters being measured from simple creditworthiness to comprehensive spending capacity. This parameter expansion maintains operational simplicity through automated modeling while significantly improving spending capacity estimation accuracy.
Solution Approach 2:
The system creates a virtual copy of the customer's complete financial profile by aggregating data from multiple sources (credit bureaus, tradelines, financial statements) into a unified spending behavior model. This copied comprehensive profile enables accurate spending capacity estimation without requiring complex manual assessment procedures, maintaining ease of operation while improving precision.
Data Source
AI summary
Commercial size of spending wallet (“CSoSW”) is the total business spend of a business including cash but excluding bartered items. Commercial share of wallet (“CSoW”) is the portion of the spending wallet that is captured by a particular financial company. A modeling approach utilizes various data sources to provide outputs that describe a company's spend capacity. Marketing companies that sell lists compile those lists by searching one or more databases for names and/or businesses that match certain criteria. Those marketing companies can use the CSoW/CSoSW modeling approach to show predicted spend and/or revenues for each company on a list. This makes the list more valuable to list buyers.