17937372. GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE simplified abstract (Capital One Services, LLC)
Contents
- 1 GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE - 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
GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE
Organization Name
Inventor(s)
Samuel Sharpe of Cambridge MA (US)
Christopher Bayan Bruss of Washington DC (US)
Brian Barr of Schenectady NY (US)
GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17937372 titled 'GENERATING COUNTERFACTUAL SAMPLES BASED ON USER PREFERENCE
Simplified Explanation
The abstract describes a computing system that uses machine learning and counterfactual samples to generate explanations for model predictions, train models to be consistent with previous models, and create counterfactual samples based on user preferences.
- The computing system aggregates multiple counterfactual samples for generating machine learning explanations.
- It uses machine learning and counterfactual samples to determine text for model prediction explanations.
- The system trains models to determine action acceptance and generate consistent output.
- It generates counterfactual samples based on user preferences by adjusting features indicated by the preferences.
Potential Applications
This technology could be applied in various fields such as finance, healthcare, and marketing for providing transparent explanations for machine learning predictions.
Problems Solved
This technology addresses the need for interpretable machine learning models, consistent model outputs, and personalized counterfactual samples based on user preferences.
Benefits
The benefits of this technology include improved transparency in machine learning models, increased trust in model predictions, and personalized explanations for users.
Potential Commercial Applications
A potential commercial application of this technology could be in the development of AI-powered decision-making systems for businesses that require transparent and consistent model outputs.
Possible Prior Art
One possible prior art in this field is the use of counterfactual explanations in machine learning models to improve interpretability and trust in predictions.
What are the specific user preferences that can be used to generate counterfactual samples in this technology?
Specific user preferences such as desired outcomes, constraints, or ethical considerations can be used to generate counterfactual samples in this technology.
How does this technology ensure consistency in model outputs with previous machine learning models?
This technology ensures consistency in model outputs with previous machine learning models by training the models to generate outputs that align with the outputs of previous models.
Original Abstract Submitted
In some aspects, a computing system may aggregating multiple counterfactual samples so that machine learning explanations can be generated for sub-populations. In addition, methods and systems described herein use machine learning and counterfactual samples to determine text to use in an explanation for a model's prediction. A computing system may also train machine learning models to not only determine whether a request to perform an action should be accepted, but also to generate output that is consistent with output generated by previous machine learning models. Further, a computing system may generate counterfactual samples based on user preferences. A computing system may obtain preferences and then apply a penalty or adjustment parameter such that when a counterfactual sample is created, the computing system is forced to change one or more features indicated by the preferences to create the counterfactual sample.
