Dynamic GUI for Financial Model Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing loan access systems fail to effectively determine personalized financial models that allow users to achieve their financial objectives by modifying their current financial information to a future, predetermined state within a specified time frame.
Innovation Solution
A loan access system that determines a user's current financial information and financial objectives, generates a personalized financial model using machine learning, and provides a platform for lenders to offer loan products that align with the user's objectives, allowing users to modify their financial information to achieve previously inaccessible loans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the system provides a comprehensive platform for lenders to bid for loan products and uses machine learning to generate personalized financial models, then the ability to access previously inaccessible loans is improved, but the system complexity and computational resources required increase significantly
Solution Approach 1:
The system segments the complex loan matching process into distinct modules: a financial model generation module that creates personalized financial models using machine learning, a loan product module that defines loan parameters, and a matching module that compares models with loan products. This segmentation allows each component to be developed and optimized independently while maintaining overall system adaptability.
Solution Approach 2:
The patent introduces a financial model as an intermediary representation between user financial information and loan products. Instead of directly comparing raw financial data with loan criteria, the system generates standardized financial models that serve as mediators, simplifying the matching process while improving loan accessibility through personalized analysis.
2Measurement precision
If the system generates personalized financial models using machine learning trained on multiple users' information, then the precision of financial modeling is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-generating multiple possible financial models based on current financial information and projected future states. These models are created in advance before loan product matching begins, allowing the machine learning algorithms to work on data preparation and feature extraction beforehand, thus reducing real-time processing requirements.
Solution Approach 2:
The patent implements a multi-stage modeling approach where financial models are generated at different levels of detail. A preliminary model is created quickly for initial screening, and more comprehensive models are generated only when needed for specific loan products or when preliminary models indicate potential matches. This partial action approach balances accuracy with processing efficiency.
Data Source
AI summary
Embodiments disclosed herein are directed to a computerized method that includes operations of generating a graphical user interface (GUI) displaying parameters of a financial objective and a plurality of financial model icons, wherein each of the plurality of financial model icons lists a credit score and a corresponding payment and receiving, by the GUI, user input modifying a first parameter of the financial objective. Additional operations include dynamically updating one or more of the plurality of financial model icons, and altering the GUI based on the dynamically updating of the plurality of financial model icons resulting in an adjustment of a positioning of a first financial model icon. Adjustment of the positioning of the first financial model icon may include positioning the first financial model icon proximate the first parameter, wherein an advantage provided by a first financial model represented by the first financial model icon corresponds the first parameter.