Unified Risk Scoring Optimization for Front-Back Decision Consistency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Businesses face challenges in using two different risk scores for front-end and back-end assessments, leading to inconsistent decision-making and negative public relations when selecting recipients for offers and later declining responders based on different criteria.
Innovation Solution
A unified scoring system is developed using an optimization process that combines front-end and back-end risk scores through iterative processing, employing the Kolmogorov-Smirnov test to determine optimal weighting parameters, ensuring the unified score outperforms benchmark scores and meets both assessment objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If two different risk scores are used for front-end and back-end assessments, then each assessment can be optimized for its specific goal, but decision-making consistency and public relations are worsened
Solution Approach 1:
The patent combines two separate risk scores (front-end and back-end) into a single unified risk score through a scoring optimization system. This unified score integrates the assessment criteria from both stages, allowing consistent decision-making across front-end offer selection and back-end credit approval while maintaining the optimization benefits of both original assessments.
2Adaptability or versatility
If separate scores are used for front-end and back-end, then each score can be tailored to specific criteria, but the system complexity increases
Solution Approach 1:
The unified risk score serves multiple functions: it is used for both front-end offer selection and back-end credit approval decisions. The scoring optimization system is designed to be adaptable, allowing the unified score to reflect different assessment priorities through configurable parameters while maintaining a single, consistent scoring mechanism that reduces overall system complexity.
3Reliability
If iterative processing with optimization is applied, then the unified score performance is improved, but the processing time increases
Solution Approach 1:
The scoring optimization system performs preliminary calculations and weight determinations in advance, establishing optimized weighting factors before actual scoring operations. This preliminary action allows the iterative optimization to be executed more efficiently during live processing, reducing the time required to generate unified scores while maintaining high performance through the optimization process.
Data Source
AI summary
Systems and methods relate to generating a unified determination based on a subdetermination, and in particular, generating a unified score based on respective scores. For example, the invention provides a method for generating a unified determination based on subdeterminations, the method including generating a first subdetermination based on first criteria; generating a second subdetermination based on second criteria; and generating a unified determination based on the first subdetermination and the second subdetermination. The generation of the unified determination includes (a) assigning, using iterative processing, an assigned weighting respectively to the first determination and second determination; (b) determining if the assigned weighting satisfies at least one constraint; (c) comparing the assigned weighting to an optimized weighting, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting; and (d) if the assigned weighting is improved, then assigning the assigned weighting to be the optimized weighting.