Enterprise Risk Prediction Using Multi-Level Conduction Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing enterprise risk prediction models struggle to accurately separate inherent risk from conduction risk and fail to account for complex, time-varying association relationships between enterprises, leading to inaccurate risk conduction predictions.
Innovation Solution
A method involving determining inherent risk probability, building a relationship graph, calculating primary and multi-level conduction probabilities, and integrating these with the inherent risk probability to predict a target risk probability, using machine learning techniques like automatic modeling and conduction probability models trained with labeled conduction sample pairs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing enterprise risk prediction models are used, then risk prediction can be performed, but the accuracy is insufficient due to inability to separate inherent risk from conduction risk and failure to account for complex association relationships
Solution Approach 1:
The patent segments the risk prediction model into two distinct components: an inherent risk prediction model that assesses the target enterprise's own risk characteristics, and a conduction risk prediction model that evaluates risk transmission from associated enterprises. This segmentation allows each model to focus on specific aspects of risk, improving overall prediction accuracy while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent introduces an association relationship graph as an intermediary structure that captures complex relationships between enterprises. This graph serves as a mediator that connects the target enterprise with its associates, enabling the conduction risk model to systematically evaluate risk transmission pathways without requiring direct complex interactions between all entities.
2Measurement precision
If complex association relationships between enterprises are accounted for, then risk conduction prediction accuracy improves, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent performs preliminary action by pre-establishing the association relationship graph before risk prediction. This graph预先 captures the structural relationships between enterprises, allowing the model to efficiently query and process risk conduction pathways without performing complex relationship analysis during the actual prediction phase, thereby reducing real-time computational burden.
Solution Approach 2:
The patent transforms the complex multi-dimensional enterprise relationship data into a structured graph representation with nodes and edges. This dimensional transformation organizes chaotic association data into a manageable structure, making it easier to detect and measure risk conduction pathways while maintaining accuracy in capturing complex relationships.
Data Source
AI summary
A method and apparatus for predicting a risk are provided. The method may include: determining an inherent risk probability of a to-be-tested object; building a relationship graph between the to-be-tested object and different associated objects; determining a primary conduction probability between any two directly associated objects in the relationship graph; determining, based on the primary conduction probability between any two directly associated objects in the relationship graph and the relationship graph, a multi-level conduction probability of the to-be-tested object; and determining a target risk probability of the to-be-tested object, based on the inherent risk probability and the multi-level conduction probability of the to-be-tested object.