Supplier Onboarding Prediction via Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional commercial credit card onboarding campaigns rely on generic industry data, leading to inefficiencies in predicting supplier acceptance and developing effective strategies, as they do not account for specific supplier data and past campaign outcomes.

Innovation Solution

The implementation of a Supplier Analysis and Onboarding (SAO) unit that analyzes customer and financial institution data from multiple sources to predict supplier acceptance likelihood, transaction volume conversion, and develop targeted campaign strategies based on supplier industry type, transaction characteristics, and past campaign results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If generic industry data is used for predicting supplier acceptance, then the system is simpler to operate, but the prediction accuracy deteriorates

Engineering Contradiction:

Improvesimplicity of onboarding campaignVSAvoidprediction accuracy of supplier acceptance

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments suppliers into different profiles based on multiple characteristics (industry type, transaction characteristics, past campaign responses) rather than treating all suppliers uniformly. This segmentation enables more accurate predictions by analyzing specific subsets of suppliers with similar attributes, resolving the contradiction between system simplicity and prediction accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the parameters used for prediction from generic industry-level data to specific supplier-level parameters including transaction characteristics, industry type, and historical campaign responses. This parameter transformation enables more precise predictions while maintaining operational simplicity through automated analysis of these parameters.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If specific supplier data and past campaign data are analyzed, then the prediction accuracy improves, but the system complexity increases

Engineering Contradiction:

Improveprediction accuracy of supplier acceptanceVSAvoidcomplexity of data analysis system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically collecting, analyzing, and processing supplier data and past campaign outcomes without requiring manual intervention. The automated analysis of multiple data sources (customer data, financial institution data, third-party data) reduces system complexity from the user perspective while maintaining high prediction accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system is designed to handle multiple functions: collecting data from various sources, analyzing transaction characteristics, determining supplier profiles, and predicting acceptance likelihood. This multi-functional design consolidates what would otherwise be separate complex systems into a single unified platform, managing complexity while improving accuracy.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Productivity

If comprehensive data from multiple sources is collected and analyzed, then the onboarding effectiveness improves, but the resource consumption increases

Engineering Contradiction:

Improveonboarding effectivenessVSAvoidresource usage for campaigns

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of supplier data and past campaign outcomes before launching onboarding campaigns. By pre-determining supplier profiles and acceptance likelihoods based on historical data, the system identifies the most promising targets in advance, enabling more effective campaigns that convert fewer resources into higher onboarding success rates.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback from past campaign outcomes into future predictions by analyzing historical data on supplier responses to onboarding efforts. This feedback loop allows the system to learn from previous resource investments and optimize future campaign strategies, improving onboarding effectiveness while reducing wasted resources on low-probability targets.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11436608B1Commercial credit card system

Publication Date: 2022.09.06 WELLS FARGO BANK NA

AI summary

One or more interfaces receive, from one or more sources, supplier data, comprising transactional data and an industry type, and supplier profile data, comprising supplier acceptance category information, associating each of a plurality of predetermined supplier acceptance categories with one or more industry types, and profile type information, associating each of a plurality of predetermined profile types with one or more transaction characteristics of a plurality of transaction characteristics and one or more supplier acceptance categories of the plurality of predetermined supplier acceptance categories. One or more processors determine: a transaction characteristic associated with the transactions based on the transactional data; a supplier acceptance category associated with the supplier based on the industry type and the supplier acceptance category information; and a profile type associated with the supplier based on the transaction characteristic, the supplier acceptance category, and the profile type information; and output the profile type.