18079486. Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms simplified abstract (GOOGLE LLC)
Contents
- 1 Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms - 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
Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms
Organization Name
Inventor(s)
Madhav Datt of Mountain View CA (US)
Surabhi Choudhary of Chennai (IN)
Nikhil Shirish Ketkar of Bengaluru (IN)
Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms - A simplified explanation of the abstract
This abstract first appeared for US patent application 18079486 titled 'Automated, Constraints-Dependent Machine Learning Model Thresholding Mechanisms
Simplified Explanation
The abstract describes a patent application for a computing system that performs discrete-valued output classification using machine learning models and threshold values. The system determines the final threshold value based on performance values and safeguard criteria, and then uses this threshold value to authenticate input data.
- The system obtains a candidate threshold value for a data slice.
- It calculates a performance value using a machine-learned model and the candidate threshold value.
- If the safeguard criterion is not satisfied, a tradeoff logic operation is performed to determine the final threshold value.
- The final threshold value is used to determine the authenticity of input data.
Potential Applications
This technology could be applied in fraud detection systems, security authentication processes, and data validation tools.
Problems Solved
This technology helps in accurately classifying and authenticating data, reducing false positives and enhancing data security.
Benefits
The system provides a reliable method for classifying data and determining its authenticity, leading to improved data security and fraud prevention.
Potential Commercial Applications
Commercial applications of this technology include financial institutions, e-commerce platforms, and cybersecurity companies for enhancing data security measures.
Possible Prior Art
Prior art in this field may include existing machine learning models for data classification and authentication, as well as threshold determination algorithms used in various industries.
Unanswered Questions
How does this technology compare to existing fraud detection systems in terms of accuracy and efficiency?
This article does not provide a direct comparison with existing fraud detection systems, so it is unclear how this technology performs in relation to them.
What are the potential limitations or challenges in implementing this technology in real-world applications?
The article does not address any potential limitations or challenges that may arise when implementing this technology, leaving room for further exploration in this area.
Original Abstract Submitted
Provided are computing systems, methods, and platforms for a discrete-valued output classification. The operations can include obtaining a candidate threshold value for a first slice in a plurality of data slices. Additionally, the operations can include calculating, using a candidate machine-learned model and the candidate threshold value, a first performance value associated with a first risk tolerance value. Moreover, the operations can include determining, based on the first performance value, that a safeguard criterion for the first slice has not been satisfied. In response to the determination that the safeguard criterion for the first slice has not been satisfied, the operations can include performing a tradeoff logic operation to determine the final threshold value. Subsequently, the operations can include determining, using the candidate machine-learned model, whether input data is authentic based on the final threshold value.
