US-20260127594-A1 - COMPUTER-BASED SYSTEMS CONFIGURED TO AUTOMATICALLY EXECUTE PROGRAMMED ROUTINES BASED ON PRE-DETERMINED EVENT TRIGGERS AND METHODS OF USE THEREOF

US20260127594A1US 20260127594 A1US20260127594 A1US 20260127594A1US-20260127594-A1

Abstract

In some embodiments, the present disclosure provides an exemplary method that may include steps of obtaining usage data associated with a plurality of data sets over a predetermined period of time; determining a correlation between one data point in a plurality of data points associated with each data set within the usage data and an established usage baseline, the established usage baseline is associated with a historical data set; utilizing a trained machine learning module to dynamically generate a usage score for the plurality of data sets based on the correlation between the data point and the established usage baseline to form a prediction of usage data; and automatically modifying a particular data set of the plurality of data sets to form a modified data set, the modified data set comprising additional authentication steps to perform a plurality of actions.

Inventors

Matthew Louis Nowak
Robert Dwane Wokaty, Jr.
David Crawford
Taylor TURNER

Assignees

CAPITAL ONE SERVICES, LLC

Dates

Publication Date: 20260507
Application Date: 20241104

Claims (20)

1 . A computer-implemented method comprising: obtaining, by a processor, usage data associated with a plurality of data sets over a predetermined period of time; determining, by the processor, a correlation between one data point in a plurality of data points associated with each data set within the usage data and an established usage baseline, the established usage baseline is associated with a historical data set; utilizing, by the processor, a trained machine learning module to dynamically generate a usage score for the plurality of data sets based on the correlation between the data point and the established usage baseline to form a prediction of usage data; and automatically modifying, by the processor and in response to the prediction of usage data exceeding a predetermined threshold of usage, a particular data set of the plurality of data sets to form a modified data set, the modified data set comprising additional authentication steps to perform a plurality of actions.
2 . The method of claim 1 , wherein the usage data comprises account information associated with a particular account tied to a particular computing device.
3 . The method of claim 1 , wherein the usage data associated with the plurality of data sets comprises user-specific usage data.
4 . The method of claim 1 , wherein the predetermined period of time comprises a range of time with a minimum limit of at minutes and a maximum limit of months.
5 . The method of claim 1 , wherein the obtaining the usage data comprises: continuously monitoring activity associated with the plurality of data sets, wherein the activity comprises a plurality of transactions utilizing transfers of data stored in the particular data set; identifying a type of transaction associated with each transaction in the plurality of transactions; and comparing each transaction within a particular type of transaction to an aggregate rate matrix to assign a weight to each transaction for a proportional redeemable value.
6 . The method of claim 1 , wherein the trained machine learning module comprises a need multiplier rules engine.
7 . The method of claim 1 , wherein the particular data point within the usage data comprises an identified transaction that aligns with a predetermined transaction type associated with the trained machine learning module.
8 . The method of claim 1 , wherein the usage score comprises a proportional value applicable to the plurality of data sets based on an assigned weight via an aggregate weight matrix associated with a need multiplier rules engine.
9 . The method of claim 1 , wherein the plurality of data sets comprises at least one transactional data set associated with an external computing device.
10 . The method of claim 1 , wherein the established usage baseline comprises historical usage data associated with the plurality of data sets collected over multiple periods of time prior to obtaining a current user-specific usage data.
11 . The method of claim 1 , further comprising dynamically retraining the machine learning module after an expiration of the predetermined period of time with the usage score.
12 . The method of claim 11 , wherein the dynamically retraining the machine learning module by: updating the trained machine learning module with an aggregate weight matrix; determining a value proportional to an accumulation of a plurality of transactions within a particular type of transaction associated with the plurality of data sets; and automatically reducing a number of additional authentications steps proportional to the value of the plurality of transactions.
13 . The method of claim 12 , wherein the aggregate weight matrix comprises a plurality of weights associated with each type of transaction of the plurality of transactions within the usage data.
14 . The method of claim 1 , further comprising generating, via a graphical user interface located within a computing device associated with the user, a notification to detail the modified data set.
15 . A computer-implemented method comprising: obtaining, by a processor, usage data associated with a plurality of data sets over a predetermined period of time; determining, by the processor, a correlation between one data point associated with each data set within the usage data and an established usage baseline, the established usage baseline is associated with a historical data set; utilizing, by the processor, a need multiplier rules engine to dynamically generate a usage score for the plurality of data sets based on the correlation between the set of data points and the established usage baseline to form a prediction of usage data; automatically modifying, by the processor and in response to the prediction of usage data exceeding a predetermined threshold of usage, a particular data set of the plurality of data sets to form a modified data set, the modified data set comprising additional authentication steps to perform a plurality of actions; and generating, by the processor and via a graphical user interface located within a computing device, a notification detailing the modified data set.
16 . The method of claim 15 , wherein the obtaining the usage data comprises: continuously monitoring activity associated with the plurality of data set, wherein the activity comprises a plurality of transactions utilizing transfers of data stored in the particular data set; identifying a type of transaction associated with each transaction in the plurality of transactions; and comparing each transaction within a particular type of transaction to an aggregate rate matrix to assign a weight to each transaction for a proportional redeemable value.
17 . The method of claim 15 , wherein the need multiplier rules engine comprises a trained machine learning module.
18 . The method of claim 15 , further comprising automatically modifying the particular data set by: updating a trained machine learning module with an aggregate weight matrix; determining a value proportional to an accumulation of a plurality of transactions within a particular type of transaction associated with the plurality of data sets; and automatically reducing a number of additional authentications steps proportional to the value of the plurality of transactions.
19 . A system comprises: a non-transient computer memory, storing software instructions; and at least one processor of a first computing device associated with a user; wherein, when the processor executes the software instructions, the first computing device is programmed to: obtain usage data associated with a plurality of data sets over a predetermined period of time; determine a correlation between one data point in a plurality of data points associated with each data set within the usage data and an established usage baseline, the established usage baseline is associated with a historical data set; utilize a trained machine learning module to dynamically generate a usage score for the plurality of data sets based on the correlation between the data point and the established usage baseline to form a prediction of usage data; and automatically modify, in response to the prediction of usage data exceeding a predetermined threshold of usage, a particular data set of the plurality of data sets to form a modified data set, the modified data set comprising additional authentication steps to perform a plurality of actions.
20 . The system of claim 19 , wherein the software instructions further comprise the automatically modify the particular data set by: updating the trained machine learning module with an aggregate weight matrix; determining a value proportional to an accumulation of a plurality of transactions within a particular type of transaction associated with the plurality of data sets; and automatically reducing a number of additional authentications steps proportional to the value of the plurality of transactions.

Description

FIELD OF TECHNOLOGY The present disclosure generally relates to computer-based systems configured to automatically execute programmed routines based on pre-determined event triggers and methods of use thereof. BACKGROUND OF TECHNOLOGY Typically, the training of a machine learning model requires a computing device to gather and prepare data, select an appropriate machine learning algorithm, divide data into training and testing data sets, train the model using the training data and optimize parameters, and assess how well the model performs using the testing data. SUMMARY OF DESCRIBED SUBJECT MATTER In some embodiments, the present disclosure may provide an exemplary technically improved computer-based method that includes at least the following steps: obtaining, by one or more processors, usage data associated with a user over a predetermined period of time; utilizing, by one or more processors, a trained machine learning module to determine a correlation between a particular data point within the usage data and an established usage baseline associated with the user; dynamically generating, by one or more processors, a recommendation for the user based on the correlation between the particular data point and the established usage baseline; and automatically applying, by one or more processors, the generated recommendation to an account of the user. In some embodiments, the present disclosure may provide a technically-improved computer-based system that includes a processor capable of instructing at least the following steps: obtain usage data associated with a user over a predetermined period of time; utilize a trained machine learning module to determine a correlation between a particular data point within the usage data and an established usage baseline associated with the user; dynamically generate a recommendation for the user based on the correlation between the particular data point and the established usage baseline; and automatically apply the recommendation to an account of the user. BRIEF DESCRIPTION OF DRAWINGS Various embodiments of the present disclosure can be further explained with reference to the attached drawings, wherein like structures are referred to by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed upon illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ one or more illustrative embodiments. FIG. 1 depicts a block diagram of an exemplary computer-based system and platform for automatically applying a recommendation in response to identifying a plurality of transactions during a period of time, in accordance with one or more embodiments of the present disclosure. FIG. 2 is a flowchart illustrating operational steps for automatically applying a generated recommendation to an account of a user, in accordance with one or more embodiments of the present disclosure. FIG. 3 is a flowchart illustrating operational steps for dynamically modifying the application of the generated recommendation, in accordance with one or more embodiments of the present disclosure. FIG. 4 depicts a block diagram of an exemplary computer-based system/platform in accordance with one or more embodiments of the present disclosure. FIG. 5 depicts a block diagram of another exemplary computer-based system/platform in accordance with one or more embodiments of the present disclosure. FIGS. 6 and 7 are diagrams illustrating implementations of cloud computing architecture/aspects with respect to which the disclosed technology may be specifically configured to operate, in accordance with one or more embodiments of the present disclosure. DETAILED DESCRIPTION Various detailed embodiments of the present disclosure, taken in conjunction with the accompanying figures, are disclosed herein; however, it is to be understood that the disclosed embodiments are merely illustrative. In addition, each of the examples given in connection with the various embodiments of the present disclosure is intended to be illustrative, and not restrictive. Throughout the specification, the following terms take the meanings explicitly associated herein, unless the context clearly dictates otherwise. The phrases “in one embodiment” and “in some embodiments” as used herein do not necessarily refer to the same embodiment(s), though it may. Furthermore, the phrases “in another embodiment” and “in some other embodiments” as used herein do not necessarily refer to a different embodiment, although it may. Thus, as described below, various embodiments may be readily combined, without departing from the scope or spirit of the present disclosure. In addition, the term “based on” is not exclusive and allows for being based on additional factors not described, unless th