Hierarchical Optimization for Financial Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial institutions face challenges in efficiently optimizing complex, non-linear objectives with multiple variables and constraints, such as minimizing tax liability and maximizing retirement contributions, due to the computational intensity and rigidity of existing systems, which often require significant processing resources and time, and are not capable of handling multiple sub-objectives or combinations of objectives effectively.
Innovation Solution
A hierarchical optimization method and system that processes objectives sequentially and iteratively, determining an ordered set of stages, updating fixed inputs with variable inputs from previous stages, and using optimizers to calculate optimal values, reducing the search space and computational resources needed to generate results efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If non-linear computations are used to solve complex financial objectives with multiple variables and constraints, then the accuracy of optimization results is improved, but the computing resources consumed and time required increase significantly
Solution Approach 1:
The patent segments the optimization process into multiple stages, where each stage optimizes a subset of variables rather than all variables simultaneously. This segmentation reduces the computational complexity of each individual optimization step while maintaining overall optimization accuracy through iterative refinement across stages.
Solution Approach 2:
The patent applies preliminary action by performing initial optimizations on variable subsets before combining results. The system pre-processes the optimization problem by dividing it into manageable stages, establishing initial solutions that are then refined iteratively, reducing the total computational burden compared to solving the complete problem in one step.
2Device complexity
If existing hard-coded systems are used for specific objectives, then the system structure is simplified, but the adaptability to handle different combinations of customer objectives is reduced
Solution Approach 1:
The patent implements universality by creating a system that can handle multiple different objective combinations through a common framework. The optimization system is designed to accept various objective functions and constraints dynamically, allowing it to adapt to different customer needs (tax minimization, retirement optimization, etc.) without requiring separate hard-coded systems for each scenario.
Solution Approach 2:
The patent applies dynamics by making the system configuration flexible and adjustable. Rather than hard-coding specific objectives, the system dynamically adapts to different objective combinations by receiving user-defined parameters and configuring the optimization process accordingly, enabling both simplicity and versatility.
3Reliability
If existing optimizers are used to optimize non-linear mathematical expressions, then the optimization capability is provided, but the time required exceeds feasible limits for practical scenarios
Solution Approach 1:
The patent segments the variable set into multiple subsets that are optimized in separate stages. Each stage optimizes a portion of the variables while holding others fixed, dramatically reducing the computational time required for each optimization step compared to optimizing all variables simultaneously, while still achieving reliable results through iterative refinement.
Solution Approach 2:
The patent applies partial action by optimizing variable subsets iteratively rather than attempting to optimize all variables to perfect precision in a single step. The system achieves sufficient optimization accuracy through multiple passes over variable subsets, reducing total processing time while maintaining reliable results.
Data Source
AI summary
Certain aspects of the present disclosure provide techniques for hierarchical optimization including: receiving a request to optimize a primary objective; determining a set of stages to optimize the primary objective; for each respective stage of the set of stages: determining an objective function; when the respective stage is the first stage to be processed: determining values of a set of variable inputs to the respective stage and an output of the objective function; when the respective stage is not the first stage: updating a set of fixed inputs to the respective stage by including the variable inputs to one or more previously processed stages and their corresponding values to the set of fixed inputs to the respective stage; determining values of the set of variable inputs to the respective stage and output of the objective function for the respective stage; providing a final output for display on a display device.