18072042. Automatic Alert Dispositioning using Artificial Intelligence simplified abstract (Bank of America Corporation)
Contents
Automatic Alert Dispositioning using Artificial Intelligence
Organization Name
Inventor(s)
Yvonne Li of Jersey City NJ (US)
Franklin Kaiyuen Chan of Fort Lee NJ (US)
Min Kyung Kim of Jersey City NJ (US)
Jared Scott Ginsberg of New York NY (US)
Aaron Blogg of New York NY (US)
Automatic Alert Dispositioning using Artificial Intelligence - A simplified explanation of the abstract
This abstract first appeared for US patent application 18072042 titled 'Automatic Alert Dispositioning using Artificial Intelligence
Simplified Explanation
The system utilizes machine learning techniques to identify and close false positive alerts efficiently.
- Clustering and multi-labeling classification are used to categorize prior text-based notes.
- Weak labeling, AI transformers/sentence transformation, and/or k-means cluster analysis condense large quantities of textual data into ML model components.
- Customer relationship management (CRM) platform and Risk Management Supervision (RMS) note analysis reduce redundancies in future advisory efforts.
- Numerical features output by various ML techniques improve alert triaging performance.
- Streamlining the presentation of textual data to reviewers as individual sentences or numerical values enhances explainability.
---
- Potential Applications
This technology can be applied in various industries such as finance, healthcare, and cybersecurity for efficient alert management and false positive identification.
- Problems Solved
This technology addresses the issue of wasting system resources on false positive alerts and improves the overall efficiency of alert triaging processes.
- Benefits
The benefits of this technology include improved system performance, reduced redundancies, and enhanced interpretability of large textual data.
- Potential Commercial Applications
Potential commercial applications of this technology include integration into CRM platforms, risk management systems, and other alert management tools for enhanced operational efficiency.
- Possible Prior Art
One possible prior art for this technology could be existing alert management systems that use rule-based approaches rather than machine learning techniques.
---
- Unanswered Questions
- How does this technology compare to traditional rule-based alert management systems?
This article does not provide a direct comparison between this technology and traditional rule-based alert management systems in terms of performance, efficiency, and accuracy.
- What are the potential limitations or challenges of implementing this technology in real-world systems?
The article does not address the potential limitations or challenges of implementing this technology in practical applications, such as data privacy concerns, scalability issues, or integration complexities.
Original Abstract Submitted
The system identifies false positives about a user and closes resulting alerts before the alert wastefully consume system resources. Machine learning techniques including clustering and multi-labeling classification are used to effectively categorize prior text-based notes to efficiently identify and automatically close false positive alerts. Moreover, weak labeling, AI transformers/sentence transformation, and/or k-means cluster analysis provide a means for condensing large quantities of textual data into ML model components with improved interpretability. Customer relationship management (CRM) platform and Risk Management Supervision (RMS) note analysis captures inefficiently/ineffectively organized past work and leverages it to reduce redundancies in future expert user/supervisory/customer advisory efforts. The various ML techniques disclosed herein output numerical features that directly improve model performance for alert triaging as a whole. Streamlining the presentation of large textual data to reviewers/users (e.g., supervision principals) as individual sentences or numerical values greatly improves explainability as a byproduct.
