Causality Search With Bootstrap Graph Aggregation and Edge Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional causality search programs face reliability issues and increased user burden due to loop formation and the need to select directed edges as the number of variables increases, especially when generating multiple datasets through sampling.
Innovation Solution
A causality search system that generates multiple sample datasets from an original dataset, allowing for the determination of a single causal graph through switchable graph and directed edge selection modes, which includes displaying frequency of occurrence and probability of edges to reduce user workload.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple causal graphs are generated from multiple sampled datasets, then the reliability of the causal graph is improved, but the complexity of selecting the appropriate causal graph increases
Solution Approach 1:
The system automatically determines the final causal graph by selecting directed edges with occurrence probabilities of 0.5 or higher from multiple generated causal graphs, eliminating the need for user intervention in the selection process and reducing operational complexity while maintaining reliability through statistical aggregation
Solution Approach 2:
The patent introduces a threshold parameter (occurrence probability of 0.5) to automatically filter and select directed edges from multiple causal graphs, transforming the subjective selection process into an objective parameter-based determination that reduces complexity while preserving reliability
2Quantity of substance
If the number of variables increases, then the complexity of the dataset increases, but the burden on users to select directed edges becomes heavier
Solution Approach 1:
The system automatically selects directed edges based on occurrence probability thresholds without requiring user input for each variable combination, making the operation increasingly easy as the number of variables increases while maintaining consistent reliability through statistical aggregation
Solution Approach 2:
The system provides feedback in the form of occurrence probabilities for each directed edge, allowing automatic selection based on quantitative metrics rather than subjective judgment, which scales efficiently with increasing numbers of variables
Data Source
AI summary
First, a plurality of sample datasets is generated from a single original dataset through sampling with replacement. Next, a plurality of causal graphs each showing a causal relationship between the variables using a directed edge is obtained by conducting causality search on each of the plurality of sample datasets. Then, a single causal graph is determined on the basis of the plurality of causal graphs. Thus, it is possible to improve the reliability of the causal graph. Furthermore, a graph selection mode and a directed edge selection mode are switchable to each other in determining the single causal graph. Thus, it is possible to reduce a burden on a user in the work of determining the causal graph.