LASSO Feature Importance for Interpretable Supply Chain Graph Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing supply chain machine learning systems generate convoluted probabilistic graphical models that require significant time and resources to interpret and do not effectively assess the relative importance of features and feature classes, hindering efficient decision-making.
Innovation Solution
A probabilistic graphical model feature importance system using LASSO regression analysis to prune and bin features, generating simplified models that highlight important features and classes, enabling rapid inference and planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a Bayesian network PGM is used to model the flow of all variables through a supply chain network, then the model comprehensively represents all variables and their conditional dependencies, but the model becomes extremely dense and convoluted, requiring significant time and resources to interpret and derive meaningful inferences
Solution Approach 1:
The patent extracts and removes less important features and edges from the comprehensive Bayesian network model. This is achieved through automated feature importance assessment that identifies and eliminates redundant variables, thereby reducing model density and complexity while preserving the representation of critical supply chain relationships.
Solution Approach 2:
The patent segments the comprehensive supply chain model into distinct feature classes and groups variables by their importance and relevance. This segmentation allows the model to be divided into manageable components, making interpretation easier while maintaining comprehensive coverage of critical variables through structured organization.
2Reliability
If a Bayesian network PGM is used to model the flow of all variables through a supply chain network, then the model represents all variables and their dependencies, but the model does not assess and emphasize the relative importance of some features and feature classes, which is undesirable
Solution Approach 1:
The patent implements feedback mechanisms through automated feature importance assessment that continuously evaluates and ranks features based on their relevance to supply chain outcomes. This feedback loop identifies and emphasizes critical features while de-emphasizing less important ones, ensuring that the model maintains comprehensive representation while highlighting key variables for decision-making.
Solution Approach 2:
The patent applies visual differentiation techniques to emphasize important features and feature classes within the model. By using distinct visual representations (analogous to color changes) to highlight critical variables, the model maintains comprehensive variable representation while making importance assessment intuitive and immediate for users.
3Reliability
If all features are included in the PGM model, then the model is comprehensive, but it requires significant time and resources to interpret and derive meaningful inferences
Solution Approach 1:
The patent extracts and removes less important features from the comprehensive model through automated feature importance assessment. This extraction process eliminates redundant variables that would otherwise require time and resources to interpret, while preserving the comprehensive representation of critical supply chain variables needed for reliable decision-making.
Solution Approach 2:
The patent performs preliminary feature importance assessment and model simplification before the actual interpretation and inference processes. By pre-identifying and emphasizing critical features in advance, the system reduces the time and resources required for subsequent interpretation while maintaining model comprehensiveness for reliable outcomes.
Data Source
AI summary
Embodiments of the following disclosure provide a feature importance system and method to identify features relevant to determining whether a target variable will achieve a particular value. One example method includes generating a probabilistic graphical model to represent the performance of one or more entities in a supply chain and selecting or more target variables. The method further includes collating a list of features pertaining to the one or more selected target variables, pruning at least one of the one or more features from the list and generating one or more bins in which to distribute the one or more features in the list. The method further includes modeling a network graph incorporating the one or more features in the list and bins and determining one or more inferences pertaining to the one or more supply chain entity target variables.