17937340. SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS simplified abstract (Capital One Services, LLC)
Contents
- 1 SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS - 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
SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS
Organization Name
Inventor(s)
Brian Barr of Schenectady NY (US)
Samuel Sharpe of Cambridge MA (US)
Christopher Bayan Bruss of Washington DC (US)
SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17937340 titled 'SYSTEMS AND METHODS FOR COUNTERFACTUALS IN MACHINE LEARNING APPLICATIONS
Simplified Explanation
The abstract describes a computing system that utilizes machine learning and counterfactual samples to generate explanations for model predictions and make decisions based on user preferences.
- The computing system aggregates multiple counterfactual samples to generate machine learning explanations for sub-populations.
- It uses machine learning and counterfactual samples to determine text for explanations of model predictions.
- The system trains machine learning models to generate output consistent with previous models.
- Counterfactual samples are generated based on user preferences, with adjustments made to features indicated by these preferences.
Potential Applications
This technology could be applied in various fields such as healthcare, finance, and e-commerce for personalized recommendations, risk assessment, and decision-making processes.
Problems Solved
This technology helps in providing transparent and interpretable explanations for machine learning model predictions, ensuring consistency in model outputs, and incorporating user preferences in decision-making processes.
Benefits
The benefits of this technology include improved trust in machine learning models, personalized user experiences, and more accurate decision-making based on user preferences.
Potential Commercial Applications
Potential commercial applications of this technology include personalized marketing strategies, risk assessment tools, and recommendation systems in various industries.
Possible Prior Art
One possible prior art for this technology could be the use of counterfactual explanations in machine learning models to improve transparency and interpretability.
Unanswered Questions
The technology does not address how it ensures the privacy and security of user preferences and data in the decision-making process.
What are the limitations of using counterfactual samples in generating explanations for machine learning models?
The article does not discuss any potential limitations or challenges associated with using counterfactual samples in generating explanations for machine learning 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.
