View source for FAIR ISAAC CORPORATION (20240267239). BLOCKCHAIN-BASED MODEL GOVERNANCE AND AUDITABLE MONITORING OF MACHINE LEARNING MODELS simplified abstract

=BLOCKCHAIN-BASED MODEL GOVERNANCE AND AUDITABLE MONITORING OF MACHINE LEARNING MODELS=


==Organization Name==

[[:Category:FAIR ISAAC CORPORATION|FAIR ISAAC CORPORATION]]


[[Category:FAIR ISAAC CORPORATION]]

==Inventor(s)==

[[:Category:Scott Michael Zoldi of San Diego CA (US)|Scott Michael Zoldi of San Diego CA (US)]][[Category:Scott Michael Zoldi of San Diego CA (US)]]

[[:Category:Shafi Ur Rahman of San Diego CA (US)|Shafi Ur Rahman of San Diego CA (US)]][[Category:Shafi Ur Rahman of San Diego CA (US)]]

==BLOCKCHAIN-BASED MODEL GOVERNANCE AND AUDITABLE MONITORING OF MACHINE LEARNING MODELS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240267239 titled 'BLOCKCHAIN-BASED MODEL GOVERNANCE AND AUDITABLE MONITORING OF MACHINE LEARNING MODELS

The patent application describes a method that involves using a trained machine learning model to determine a score based on latent features, monitoring the score determination process, and comparing production statistics with reference statistics stored on a model governance blockchain to generate alerts based on any deviations.

* Trained machine learning model used to determine scores based on latent features
* Monitoring of score determination process
* Comparison of production statistics with reference statistics stored on a model governance blockchain
* Generation of alerts based on deviations between production and reference statistics
* Utilization of one or more reference assets persisted on a model governance blockchain

### Potential Applications:
This technology can be applied in various industries where monitoring and alerting based on statistical deviations are crucial, such as finance, healthcare, and cybersecurity.

### Problems Solved:
This technology addresses the need for real-time monitoring and alerting systems that can detect deviations in production statistics based on reference data.

### Benefits:
- Improved accuracy in monitoring processes
- Early detection of anomalies or deviations
- Enhanced decision-making based on real-time data analysis

### Commercial Applications:
Title: Real-time Anomaly Detection System
This technology can be utilized in financial institutions for fraud detection, in healthcare for patient monitoring, and in cybersecurity for threat detection, enhancing operational efficiency and risk management.

### Prior Art:
Researchers have explored similar methods for anomaly detection using machine learning models and blockchain technology. Further investigation into existing patents and publications in the field of anomaly detection systems can provide valuable insights.

### Frequently Updated Research:
Stay updated on advancements in machine learning algorithms for anomaly detection, blockchain technology for data governance, and real-time monitoring systems for various industries to enhance the effectiveness of this technology.

#### Questions about Latent Feature Monitoring:
1. How does the comparison of production statistics with reference statistics contribute to anomaly detection?
   - The comparison helps identify deviations in the production process that may indicate anomalies or errors.
   
2. What are the key benefits of using a model governance blockchain in this method?
   - A model governance blockchain ensures the integrity and security of reference assets, providing a reliable source for comparison and alert generation.


==Original Abstract Submitted==

a method includes determining, by a trained machine learning model, a score based at least on one or more latent features. the method also includes monitoring the determining of the score by the trained machine learning model. the monitoring includes determining one or more production statistics associated with the one or more latent features, derived variables and input data elements, and accessing one or more reference assets persisted on a model governance blockchain. the one or more reference assets includes one or more reference statistics and a threshold indicating a deviation between the one or more production statistics and the one or more reference statistics. the method also includes generating an alert based on the one or more production statistics associated with the one or more latent features meeting the threshold. related methods and articles of manufacture are also disclosed.



[[Category:H04L9/00]]
[[Category:G06N3/045]]
[[Category:G06N3/08]]
[[Category:CPC_H04L9/50]]