View source for 17528813. COMPUTER-BASED SYSTEMS CONFIGURED FOR UTILIZING MACHINE-LEARNING ENRICHMENT OF ACTIVITY DATA RECORDS AND METHODS OF USE THEREOF simplified abstract (Capital One Services, LLC)

=COMPUTER-BASED SYSTEMS CONFIGURED FOR UTILIZING MACHINE-LEARNING ENRICHMENT OF ACTIVITY DATA RECORDS AND METHODS OF USE THEREOF=


==Organization Name==

[[:Category:Capital One Services, LLC|Capital One Services, LLC]]


[[Category:Capital One Services, LLC]]

==Inventor(s)==

[[:Category:Lukiih Cuan of Washington DC (US)|Lukiih Cuan of Washington DC (US)]][[Category:Lukiih Cuan of Washington DC (US)]]

[[:Category:Lin Ni Lisa Cheng of New York NY (US)|Lin Ni Lisa Cheng of New York NY (US)]][[Category:Lin Ni Lisa Cheng of New York NY (US)]]

[[:Category:Michelle S. Olenoski of Washington DC (US)|Michelle S. Olenoski of Washington DC (US)]][[Category:Michelle S. Olenoski of Washington DC (US)]]

==COMPUTER-BASED SYSTEMS CONFIGURED FOR UTILIZING MACHINE-LEARNING ENRICHMENT OF ACTIVITY DATA RECORDS AND METHODS OF USE THEREOF - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17528813 titled 'COMPUTER-BASED SYSTEMS CONFIGURED FOR UTILIZING MACHINE-LEARNING ENRICHMENT OF ACTIVITY DATA RECORDS AND METHODS OF USE THEREOF

==Simplified Explanation==

The patent application describes a system and method for identifying potential rejection claims in completed activity records of users. Here is a simplified explanation of the abstract:

* The system determines if a completed activity record of a user contains a predictive characteristic that suggests a potential rejection claim.
* Based on this determination, the system generates a request for additional activity data related to the completed activity.
* The system receives multiple completed activity records from other users and uses them to train a machine learning model that can identify characteristics associated with known entities.
* When the predictive characteristic is present, the system applies the trained machine learning model to identify known-entity data related to the completed activity of the user.
* Finally, the system updates the completed activity record of the user's completed activity.

Potential Applications:

* Fraud Detection: The system can be used to identify potential fraudulent claims or activities by analyzing activity records and predicting rejection claims.
* Risk Assessment: By analyzing completed activity records, the system can help assess the risk associated with certain activities or claims.
* Customer Service Improvement: The system can provide insights into potential rejection claims, allowing companies to improve their customer service and address issues proactively.

Problems Solved:

* Identifying Potential Rejection Claims: The system solves the problem of identifying completed activities that may result in rejection claims, allowing for proactive measures to be taken.
* Efficient Data Analysis: By using machine learning, the system can quickly analyze large amounts of completed activity records and identify patterns or characteristics associated with potential rejection claims.

Benefits:

* Improved Efficiency: The system automates the process of identifying potential rejection claims, saving time and resources.
* Enhanced Risk Management: By identifying potential rejection claims, the system helps mitigate risks and prevent financial losses.
* Better Customer Experience: Proactively addressing potential rejection claims improves customer satisfaction and loyalty.


==Original Abstract Submitted==

Systems and methods are disclosed including determining that a first activity data of a completed activity record of a user comprises a predictive characteristic indicative of a potential rejection claim. The computing device produces a request for a second activity data of the completed activity, based at least in part on the first activity data. The computing device receives a plurality of completed activity records related to a plurality of other users and trains an entity-identifying machine learning model to identify a plurality of entity-identifying characteristics related to a plurality of known entities to obtain a trained entity-identifying machine learning model. The computing device applies, when the predictive characteristic is present, the trained entity-identifying machine learning model to identify a known-entity data related to the completed activity of the user. The computing device updates the completed activity record of the completed activity of the user.



[[Category:G06N5/02]]
[[Category:G06N5/04]]
[[Category:G06Q30/02]]