18046489. OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS - 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
OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Laurent Boue of Peteh Tikva (IL)
OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18046489 titled 'OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
Simplified Explanation
The abstract describes a patent application for a machine learning model based on extreme value theory (EVT) that identifies anomalous samples by comparing generated outlier scores to a determined threshold based on a risk factor.
- The machine learning model utilizes extreme value theory (EVT) mechanisms to select a sample of data and determine a threshold based on a risk factor.
- An outlier score is generated for the sample and compared to the threshold to identify anomalous samples.
- The schema is updated based on the investigation results of the sample and risk factor.
Potential Applications
This technology could be applied in various industries such as finance, cybersecurity, and anomaly detection systems.
Problems Solved
This technology helps in efficiently identifying anomalous samples in large datasets, improving risk assessment and decision-making processes.
Benefits
The benefits of this technology include improved accuracy in anomaly detection, enhanced risk management, and better understanding of outlier behavior in data.
Potential Commercial Applications
The potential commercial applications of this technology include fraud detection systems, cybersecurity tools, and financial risk assessment platforms.
Possible Prior Art
One possible prior art could be existing machine learning models for anomaly detection in data, but the specific use of extreme value theory (EVT) mechanisms may be a novel approach.
Unanswered Questions
How does this technology compare to traditional anomaly detection methods?
This technology offers a more sophisticated approach to anomaly detection by incorporating extreme value theory (EVT) mechanisms, which may provide more accurate results in certain scenarios.
What are the limitations of this technology in real-world applications?
The limitations of this technology may include the need for large amounts of high-quality data for training the machine learning model effectively, as well as potential challenges in interpreting and implementing the threshold determined by the model.
Original Abstract Submitted
A sample of data, including a risk factor, is selected by a machine learning (ML) model of an extreme value theory (EVT) mechanism. A threshold is determined by the ML model based on the risk factor, an outlier score is generated for the sample, and the outlier score is compared to the threshold. The sample is identified as anomalous based on the generated outlier score being greater than the threshold. A schema comprising results of an investigation into the sample and the risk factor is updated based on the received schema.
