US-20260127643-A1 - COMPUTER-BASED SYSTEMS CONFIGURED FOR IDENTIFYING RESTRICTED REVERSALS OF OPERATIONS IN DATA ENTRY AND METHODS OF USE THEREOF

US20260127643A1US 20260127643 A1US20260127643 A1US 20260127643A1US-20260127643-A1

Abstract

Systems and methods of the present disclosure enable automated identification of restrictions on reversals of data entries by receiving location data from a computing device associated with a user, and utilizing a data profile classification machine learning model to classify a particular data profile according to a data profile classification type based at least in part on a history of data entries associated with the particular data profile when the physical location is within a predetermined proximity of another physical location associated with the particular data profile. A reversal rate of data entries in the history of data entries is determined for the particular data profile. An electronic activity reversal restriction is determined where the reversal rate is below a predetermined value, and a pop-up notification is presented on the computing device notifying the user of the electronic activity reversal restriction of the particular data profile.

Inventors

Abdelkader M'Hamed Benkreira
Michael Mossoba
Joshua Edwards

Assignees

CAPITAL ONE SERVICES, LLC

Dates

Publication Date: 20260507
Application Date: 20251110

Claims (20)

1 - 20 . (canceled)
21 . A method comprising: receiving, by at least one processor, contextual data from a computing device associated with a user, wherein the contextual data comprises location data representing a physical location of the computing device and web browsing data representing a website visited by the computing device; utilizing, by the at least one processor, a data profile classification machine learning model to classify a particular data profile according to a data profile classification type based at least in part on a history of data entries associated with the particular data profile, wherein the data profile classification machine learning model comprises a plurality of classification parameters trained to identify similar entities based at least in part on data profile-related data entries, and wherein the data profile-related data entries represent electronic activities and electronic activity reversals; determining, by the at least one processor, a reversal rate of data entries in the history of data entries for the particular data profile; determining, by the at least one processor, an electronic activity reversal ranking of the data entries in the history of data entries for the particular data profile based at least in part on the reversal rate and the data profile classification type; determining, by the at least one processor, an electronic activity reversal restriction for the particular data profile when the electronic activity reversal ranking is below a predetermined threshold; and generating, by the at least one processor, a computer instruction to cause a pop-up notification including the electronic activity reversal restriction of the particular data profile to be presented to the user via the computing device, wherein at least one of the location data is within a predetermined proximity of a physical location associated with the particular data profile or the web browsing data matches a website associated with the particular data profile.
22 . The method of claim 21 , wherein the contextual data comprises only location data; and wherein the pop-up notification is generated only when the location data indicates that the computing device is within the predetermined proximity.
23 . The method of claim 21 , wherein the contextual data comprises only web browsing data; and wherein the pop-up notification is generated only when the web browsing data matches a website associated with the particular data profile.
24 . The method as recited in claim 21 , wherein determining the electronic activity reversal ranking comprises ranking a reversal rate of the particular data profile relative to reversal rates of a plurality of other data profiles.
25 . The method as recited in claim 21 , wherein determining the reversal rate comprises identifying pairs of data entries in a history of data entries that represent an electronic activity and a subsequent reversal thereof based at least in part on a measure of similarity between electronic activity features and opposite electronic activity values.
26 . The method of claim 21 , wherein the data profile classification machine learning model comprises a clustering model.
27 . The method as recited in claim 21 , wherein the data profile-related electronic activities comprise merchant transaction records; and wherein the electronic activity reversals comprise transaction refunds.
28 . The method of claim 21 , further comprising: receiving user feedback data indicating whether the electronic activity reversal restriction is accurate; and updating the classification parameters of the data profile classification machine learning model based at least in part on the user feedback data.
29 . The method of claim 21 , wherein the predetermined threshold for the electronic activity reversal ranking is dynamically adjusted based on statistical analysis of reversal rates across a plurality of data profiles.
30 . The method of claim 21 , wherein the pop-up notification further comprises information identifying the physical location or website associated with the particular data profile.
31 . A system comprising: at least one processor configured to: receive contextual data from a computing device associated with a user, wherein the contextual data comprises location data representing a physical location of the computing device and web browsing data representing a website visited by the computing device; utilize a data profile classification machine learning model to classify a particular data profile according to a data profile classification type based at least in part on a history of data entries associated with the particular data profile, wherein the data profile classification machine learning model comprises a plurality of classification parameters trained to identify similar entities based at least in part on data profile-related data entries, and wherein the data profile-related data entries represent electronic activities and electronic activity reversals; determine a reversal rate of data entries in the history of data entries for the particular data profile; determine an electronic activity reversal ranking of the data entries in the history of data entries for the particular data profile based at least in part on the reversal rate and the data profile classification type; determine an electronic activity reversal restriction for the particular data profile when the electronic activity reversal ranking is below a predetermined threshold; and generate a computer instruction to cause a pop-up notification including the electronic activity reversal restriction of the particular data profile to be presented to the user via the computing device, wherein at least one of the location data is within a predetermined proximity of a physical location associated with the particular data profile or the web browsing data matches a website associated with the particular data profile.
32 . The system of claim 31 , wherein the contextual data comprises only location data; and wherein the pop-up notification is generated only when the location data indicates that the computing device is within the predetermined proximity.
33 . The system of claim 31 , wherein the contextual data comprises only web browsing data; and wherein the pop-up notification is generated only when the web browsing data matches a website associated with the particular data profile.
34 . The system as recited in claim 31 , wherein determining the electronic activity reversal ranking comprises ranking a reversal rate of the particular data profile relative to reversal rates of a plurality of other data profiles.
35 . The system as recited in claim 31 , wherein determining the reversal rate comprises identifying pairs of data entries in a history of data entries that represent an electronic activity and a subsequent reversal thereof based at least in part on a measure of similarity between electronic activity features and opposite electronic activity values.
36 . The system of claim 31 , wherein the data profile classification machine learning model comprises a clustering model.
37 . The system as recited in claim 31 , wherein the data profile-related electronic activities comprise merchant transaction records; and wherein the electronic activity reversals comprise transaction refunds.
38 . The system of claim 31 , wherein the at least one processor is further configured to: receiving user feedback data indicating whether the electronic activity reversal restriction is accurate; and updating the classification parameters of the data profile classification machine learning model based at least in part on the user feedback data.
39 . The system of claim 31 , wherein the predetermined threshold for the electronic activity reversal ranking is dynamically adjusted based on statistical analysis of reversal rates across a plurality of data profiles.

Description

COPYRIGHT NOTICE A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever. The following notice applies to the software and data as described below and in drawings that form a part of this document: Copyright, Capital One Service, LLC, All Rights Reserved. FIELD OF TECHNOLOGY The present disclosure generally relates to computer-based systems for identifying restricted reversals of operations in data entry, including discovery of data operation practices using machine learning modeling, and methods of user thereof. BACKGROUND OF TECHNOLOGY Various data operations may have restrictions on available operations and electronic activities that may not be readily apparent to a user. For example, electronic transactions may be restricted from reversal, software navigation operations may be restricted from backtracking or from accessing certain portions of the software or system, among other scenarios. SUMMARY OF DESCRIBED SUBJECT MATTER In some embodiments, the present disclosure provides an exemplary technically improved computer-based method that includes at least the following steps of receiving, by at least one processor, location data from a computing device associated with a user, where the physical location data represents a physical location of the computing device; utilizing, by the at least one processor, a data profile classification machine learning model to classify a particular data profile according to a data profile classification type based at least in part on a history of data entries associated with the particular data profile when the physical location is within a predetermined proximity of another physical location associated with the particular data profile, where the data profile classification machine learning model includes a plurality of classification parameters trained to identify similar entities based at least in part on data profile-related data entries, where the data profile-related data entries represent data profile-related electronic activities and data profile-related electronic activity reversals; determining, by the at least one processor, a reversal rate of data entries in the history of data entries for the particular data profile; determining, by the at least one processor, an electronic activity reversal ranking of the data entries in the history of data entries for the particular data profile based at least in part on the reversal rate and the data profile classification type; determining, by the at least one processor, an electronic activity reversal restriction where the electronic activity reversal ranking is below a predetermined value; and generating, by the at least one processor, a computer instruction to the computing device to cause a pop-up notification including the electronic activity reversal restriction of the particular data profile to be presented to the user. In some embodiments, the present disclosure provides an exemplary technically improved computer-based method that includes at least the following steps of receiving, by at least one processor, web browsing data from a computing device associated with a user, where the web browsing data represents a website visited by the computing device; utilizing, by the at least one processor, a data profile classification machine learning model to classify the particular data profile according to a data profile classification type based at least in part on a history of data entries associated with the particular data profile when the web browsing data represents the website matching a data profile website associated with a particular data profile, where the data profile classification machine learning model includes a plurality of classification parameters trained to identify similar entities based at least in part on data profile-related data entries, where the data profile-related data entries represent data profile-related electronic activities and data profile-related electronic activity reversals; determining, by the at least one processor, a reversal rate of data entries in the history of data entries for the particular data profile; determining, by the at least one processor, an electronic activity reversal ranking of the data entries in the history of data entries for the particular data profile based at least in part on the reversal rate and the data profile classification type; determining, by the at least one processor, an electronic activity reversal restriction where the electronic activity reversal ranking is below a predetermined value; and generating, by the at least one processor, a computer instruction to the computing device to cause a pop-up notification including the electronic activity re