Financial Rate Optimization via Rule Segmentation and Densification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial institutions face challenges in effectively modeling and optimizing numerous business rules across millions of rate cells to maintain key performance indicators for their products, such as home equity loans and lines of credit, due to a scarcity of information and complexity in mapping rules to an optimized rate recommendation system.
Innovation Solution
A computer-implemented method that defines and optimizes rate values for target products by applying linear product rules, performing densification to infer rates for non-contributing products, and relaxing starting rates that violate rules, while aiming to achieve profit and sales volume targets within a financial system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a multitude of rate cells are maintained to provide detailed pricing options, then product pricing flexibility and coverage are improved, but system complexity and difficulty of rule mapping increase significantly
Solution Approach 1:
The patent segments the complex pricing system by introducing intermediary aggregation layers that group rate cells by product families and attributes. This hierarchical segmentation allows detailed pricing to be maintained while reducing the complexity of rule mapping through structured organization of the rate cell universe.
Solution Approach 2:
The patent introduces intermediary aggregation layers as mediators between business rules and individual rate cells. These aggregations serve as intermediate structures that simplify rule application by grouping related rate cells, thereby reducing the direct complexity of mapping rules to millions of individual rate cells while preserving pricing flexibility.
2Productivity
If optimization is performed on all rate cells, then comprehensive price optimization is achieved, but computational resources and processing time are excessively consumed
Solution Approach 1:
The patent extracts and focuses optimization efforts on only those rate cells that actively contribute to key performance indicators, rather than optimizing all rate cells. This selective extraction identifies and optimizes the critical subset of rate cells that matter for business objectives, significantly reducing computational resource consumption while maintaining optimization effectiveness.
Solution Approach 2:
The patent applies partial optimization by concentrating computational resources on the subset of rate cells that actively contribute to KPIs, rather than performing exhaustive optimization on all rate cells. This partial action approach achieves sufficient optimization for business needs while avoiding the excessive computational burden of complete optimization.
3Measurement precision
If detailed information is collected for all rate cells, then accurate optimization decisions can be made, but data collection and processing burden increase
Solution Approach 1:
The patent extracts and focuses data collection efforts on only those rate cells that actively contribute to key performance indicators. By identifying and collecting information only for the relevant subset of rate cells rather than all rate cells, the system maintains optimization accuracy for decision-making while significantly reducing the data collection and processing burden.
Data Source
AI summary
A computer system for modeling a portfolio of products in a financial system to determine the rate of a target product. The products are defined by attribute values, an attribute being any criteria that impacts product rates. Linear associated product rules are used by the computer system to create an optimized scenario of total profit and overall volume of sales for the portfolio. From the optimized scenario a rate for the target product can be determined which maintains a financial institution's strategic and business objectives. The optimizing process includes applying the associated product rules to products actively contributing to key performance indicators. Densification is then used to infer the rate for all other products in the portfolio. Finally, if the starting rate of a product violates an associated product rule, the starting rate is relaxed to avoid the violation.