17985483. DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
- 1 DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Abigail Goldsteen of Haifa (IL)
DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY - A simplified explanation of the abstract
This abstract first appeared for US patent application 17985483 titled 'DATA MINIMIZATION USING GLOBAL MODEL EXPLAINABILITY
Simplified Explanation
The embodiment in the patent application analyzes a predictive model and its input data using an explainability algorithm to determine the importance of a feature. It then generalizes the feature values, identifies an alternative feature, and maps the input data to a generalized domain based on the alternative feature.
- The embodiment analyzes feature values using a generalization function to determine a set of candidate feature values.
- An alternative feature is determined based on the set of candidate feature values, which is a generalization of the original feature.
- If the accuracy of the predictive model is above a threshold performance value, feature values in the input data that match the candidate feature values are mapped to a generalized representative value in the generalized domain.
Potential Applications
This technology could be applied in various fields such as finance, healthcare, and marketing for improving predictive modeling and decision-making processes.
Problems Solved
This technology helps in understanding the importance of features in predictive models, generalizing feature values, and improving the accuracy of predictions.
Benefits
The benefits of this technology include enhanced model explainability, improved model performance, and better decision-making based on generalized feature values.
Potential Commercial Applications
One potential commercial application of this technology could be in the development of advanced analytics software for businesses looking to optimize their predictive modeling processes.
Possible Prior Art
One possible prior art for this technology could be the use of feature importance analysis in machine learning models to understand the impact of different features on predictions.
Unanswered Questions
How does this technology handle categorical features in the input data?
This article does not address how the technology deals with categorical features in the input data and whether the generalization function can handle such data effectively.
What are the computational requirements of implementing this technology at scale?
The article does not provide information on the computational resources needed to implement this technology on large datasets and whether it can be scaled efficiently.
Original Abstract Submitted
An embodiment analyzes a predictive model and its input data for the predictive model using an explainability algorithm resulting in a feature importance value of a feature. The embodiment analyzes feature values of the feature using a generalization function resulting in a set of candidate feature values. The embodiment determines an alternative feature based on the set of candidate feature values, wherein the alternative feature is a generalization of the feature. The embodiment compares an accuracy of the predictive model to a threshold performance value and, responsive to the accuracy being above the threshold performance value, maps feature values in the input data that are in the set of candidate feature values to a generalized representative value in the generalized domain.
