US 12,314,289 B2
Aggregating data ingested from disparate sources for processing using machine learning models
Deepali Tuteja, Coppell, TX (US); Girish Wali, Flower Mound, TX (US); and David Anandaraj Arulraj, Mason, OH (US)
Assigned to CITIBANK, N.A., New York, NY (US)
Filed by CITIBANK, N.A., New York, NY (US)
Filed on Mar. 17, 2023, as Appl. No. 18/123,179.
Prior Publication US 2024/0311398 A1, Sep. 19, 2024
Int. Cl. G06F 16/28 (2019.01); G06F 16/21 (2019.01); G06F 16/25 (2019.01)
CPC G06F 16/287 (2019.01) [G06F 16/213 (2019.01); G06F 16/258 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method of aggregating data from disparate sources to output information, comprising:
maintaining, by a computing system, a plurality of machine learning (ML) models, each of the ML models corresponding to a respective function of a plurality of functions of one or more applications in use in a network environment;
transforming, by the computing system, a first plurality of datasets of a plurality of data sources over a first time period by converting a first format of the corresponding data source for each of the first plurality of datasets;
generating, by the computing system, from transforming the first plurality of datasets, a second plurality of datasets in a second format of the computing system corresponding to one of the plurality of ML models;
identifying, by the computing system, from the second plurality of datasets, a subset of datasets using a function selected from the plurality of functions associated with a utility of the function in at least one of the one or more applications in use in the network environment;
selecting, by the computing system, from the plurality of ML models, a ML model of the plurality of ML models based on the selected function, wherein the ML model is trained using a third plurality of datasets for the function from the plurality of data sources over a second time period;
applying, by the computing system, the ML model to the subset of datasets corresponding to the function selected from the plurality of functions;
generating, by the computing system, based on applying the ML model to the subset of datasets, an output including a metric for predicted usefulness indicating a degree of likelihood that the function is in use in at least one of the one or more applications in use in the network environment;
identifying, by the computing system, from a plurality of templates corresponding to the plurality of functions, a template defining a visualization of the output based on the function; and
causing, by the computing system, displaying of the visualization of the output including the metric indicating the degree of likelihood on a dashboard interface based on the template.