US-20260127450-A1 - DASHBOARD TO SELECT QUANTUM AND CLASSICAL ALGORITHMS FOR MAC PRICE OPTIMIZATION

US20260127450A1US 20260127450 A1US20260127450 A1US 20260127450A1US-20260127450-A1

Abstract

Various embodiments of the present disclosure provide an optimization model technique that improves the functionality of a computer in various aspects. The techniques comprise receiving a request that identifies an input dataset and a set of input performance parameters, extracting one or more features of the input dataset, determining a subset of target datasets from a set of historical datasets associated with an optimization model based on a comparison between the one or more features of the input dataset and one or more historical features associated with a historical dataset of the set of historical datasets, extracting a set of historical performance parameters from the subset of target datasets, and outputting an optimization model indicator corresponding to the optimization model based on a comparison between the set of historical performance parameters and the set of input performance parameters.

Inventors

Botond TARCSAY
Joao Gabriel TEIXEIRA NOGUEIRA
Ankit Agarwal
Michael R. Gibson

Assignees

OPTUM SERVICES (IRELAND) LIMITED

Dates

Publication Date: 20260507
Application Date: 20241107

Claims (20)

1 . A computer-implemented method comprising: receiving, by one or more processors, a request that identifies an input dataset and a set of input performance parameters; extracting, by the one or more processors, one or more features of the input dataset; determining, by the one or more processors, a subset of target datasets from a set of historical datasets associated with an optimization model based on a comparison between the one or more features of the input dataset and one or more historical features associated with a historical dataset of the set of historical datasets; extracting, by the one or more processors, a set of historical performance parameters from the subset of target datasets; and outputting, by the one or more processors, an optimization model indicator corresponding to the optimization model based on a comparison between the set of historical performance parameters and the set of input performance parameters.
2 . The computer-implemented method of claim 1 , wherein: (i) the optimization model is one of a plurality of optimization models associated with a knowledge database, (ii) the knowledge database comprises a plurality of historical performance entries for the optimization model that corresponds to the set of historical datasets, and (iii) a historical performance entry of the plurality of historical performance entries comprises a feature-parameter pair that identifies the one or more historical features and one or more historical performance parameters.
3 . The computer-implemented method of claim 1 , wherein determining the subset of target datasets comprises: determining a similarity score between the one or more features of the input dataset and the one or more historical features associated with the historical dataset; and responsive to the similarity score meeting or exceeding a similarity threshold, adding the historical dataset to the subset of target datasets.
4 . The computer-implemented method of claim 3 , wherein the similarity threshold identifies a percentile of the set of historical datasets.
5 . The computer-implemented method of claim 1 , wherein outputting the optimization model indicator comprises: determining a parameter-level distance between a historical performance parameter from the set of historical performance parameters and an input performance parameter of the set of input performance parameters; and determining the optimization model from a plurality of optimization models based on the parameter-level distance.
6 . The computer-implemented method of claim 5 , wherein determining the optimization model from the plurality of optimization models based on the parameter-level distance comprises: aggregating a plurality of parameter-level distances that respectively correspond to the set of input performance parameters to generate an aggregate distance measure; determining the optimization model based on a comparison between the aggregate distance measure and a plurality of aggregate distance measures respectively corresponding to the plurality of optimization models.
7 . The computer-implemented method of claim 1 , wherein the set of input performance parameters comprises at least two of: a current performance value, a target performance value, a lookback window, a variable level, a threshold delta to the target performance value, a run time threshold, or a threshold variable value.
8 . The computer-implemented method of claim 1 , wherein the request is received via a user interface that comprises a toggleable selection icon corresponding to at least one of the set of input performance parameters.
9 . The computer-implemented method of claim 8 , wherein the optimization model indicator comprises an interactive link that, responsive to selection of the interactive link, causes the input dataset to be provided as input to the optimization model.
10 . The computer-implemented method of claim 1 , wherein the one or more features of the input dataset comprises a number of a plurality of dataset entries and one or more entry features associated with a data entry of the plurality of dataset entries.
11 . The computer-implemented method of claim 10 , wherein the one or more features comprise a number of a plurality of data elements, a data type for a data element, and a key word of the data element.
12 . The computer-implemented method of claim 1 , further comprising: executing the optimization model using the input dataset to generate a prediction output; recording a set of performance parameters for the optimization model during the execution of the optimization model; initiating, via a user interface, a presentation of the prediction output and the set of performance parameters; and storing, within a knowledge database, a historical performance entry for the optimization model that comprises the set of performance parameters and the one or more features of the input dataset.
13 . A system comprising: one or more processors; and one or more memories storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: receiving a request that identifies an input dataset and a set of input performance parameters; extracting, by the one or more processors, one or more features of the input dataset; determining a subset of target datasets from a set of historical datasets associated with an optimization model based on a comparison between the one or more features of the input dataset and one or more historical features associated with a historical dataset of the set of historical datasets; extracting a set of historical performance parameters from the subset of target datasets; and outputting an optimization model indicator corresponding to the optimization model based on a comparison between the set of historical performance parameters and the set of input performance parameters.
14 . The system of claim 13 wherein: (i) the optimization model is one of a plurality of optimization models associated with a knowledge database, (ii) the knowledge database comprises a plurality of historical performance entries for the optimization model that corresponds to the set of historical datasets, and (iii) a historical performance entry of the plurality of historical performance entries comprises a feature-parameter pair that identifies the one or more historical features and one or more historical performance parameters.
15 . The system of claim 13 , wherein determining the subset of target datasets comprises: determining a similarity score between the one or more features of the input dataset and the one or more historical features associated with the historical dataset; and responsive to the similarity score meeting or exceeding a similarity threshold, adding the historical dataset to the subset of target datasets.
16 . The system of claim 13 , wherein outputting the optimization model indicator comprises: determining a parameter-level distance between a historical performance parameter from the set of historical performance parameters and an input performance parameter of the set of input performance parameters; and determining the optimization model from a plurality of optimization models based on the parameter-level distance.
17 . The system of claim 16 , wherein determining the optimization model from the plurality of optimization models based on the parameter-level distance comprises: aggregating a plurality of parameter-level distances that respectively correspond to the set of input performance parameters to generate an aggregate distance measure; determining the optimization model based on a comparison between the aggregate distance measure and a plurality of aggregate distance measures respectively corresponding to the plurality of optimization models.
18 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a request that identifies an input dataset and a set of input performance parameters; extracting, by the one or more processors, one or more features of the input dataset; determining a subset of target datasets from a set of historical datasets associated with an optimization model based on a comparison between the one or more features of the input dataset and one or more historical features associated with a historical dataset of the set of historical datasets; extracting a set of historical performance parameters from the subset of target datasets; and outputting an optimization model indicator corresponding to the optimization model based on a comparison between the set of historical performance parameters and the set of input performance parameters.
19 . The one or more non-transitory computer-readable media of claim 18 , wherein determining the subset of target datasets comprises: determining a similarity score between the one or more features of the input dataset and the one or more historical features associated with the historical dataset; and responsive to the similarity score meeting or exceeding a similarity threshold, adding the historical dataset to the subset of target datasets.
20 . The one or more non-transitory computer-readable media of claim 18 , wherein outputting the optimization model indicator comprises: determining a parameter-level distance between a historical performance parameter from the set of historical performance parameters and an input performance parameter of the set of input performance parameters; and determining the optimization model from a plurality of optimization models based on the parameter-level distance.

Description

BACKGROUND Various embodiments of the present disclosure address technical challenges related to machine learned technology, more specifically, determination of an optimization model that meets certain performance parameters for a particular dataset. In various domains, an optimization model is needed to solve various optimization problems. In many cases, determining the best model for an optimization task is a highly complex problem that requires expertise in the field. The selection of a suitable optimization model is limited by the knowledge of user's involved in the selection process, given that all optional models cannot be run without resulting in unnecessary costs and time. If the best model for an optimization task is not correctly determined, this may result in high costs, a long runtime, and suboptimal results. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 depicts an example overview of an architecture in accordance with some embodiments of the present disclosure. FIG. 2 depicts an example predictive data analysis computing entity in accordance with some embodiments of the present disclosure. FIG. 3 depicts an example client computing entity in accordance with some embodiments of the present disclosure. FIG. 4 depicts a dataflow diagram of an end-to-end optimization model selection architecture in accordance with some embodiments of the present disclosure. FIG. 5 depicts an operational example of a request in accordance with some embodiments of the present disclosure. FIG. 6 depicts an operational example of an input dataset in accordance with some embodiments of the present disclosure. FIG. 7 depicts an operational example of a user interface in accordance with some embodiments of the present disclosure. FIG. 8 depicts an operational example of a knowledge database in accordance with some embodiments of the present disclosure. FIG. 9 depicts a flowchart diagram of an optimization process in accordance with some embodiments of the present disclosure. FIG. 10 depicts a flowchart diagram of a target dataset extraction process in accordance with some embodiments of the present disclosure. FIG. 11 depicts a flowchart diagram of a parameter-level distance measure determination process in accordance with some embodiments of the present disclosure. DETAILED DESCRIPTION Various embodiments of the present disclosure provide machine learned architectures and pipelines that improve the functionality of a computer with respect to various computing tasks, including determining an optimization model for a particular dataset according to processing constraints of a computing environment. To achieve this, some embodiments of the present disclosure provide an optimization technique that extracts features from an input dataset and, using these extracted features, selects an optimization model from a set of available models for processing the input dataset. By preselecting a model, before the application of the model to the input dataset, the optimization technique may improve a computer's performance with respect to optimization tasks. This, in turn, leads to improved computer functionalities by improving the accessibility of optimization models to computers with limited resources (e.g., user device) without constraining an optimization task to such environments. Moreover, in some embodiments, the optimization technique may in integrate a feedback loop into an optimization task to continuously learn and adapt model selection techniques to different environments. For example, after a model is preselected for an optimization task, the performance of the model may be recorded, the dataset may be vectorized, and the vectorized dataset may be stored with parameters reflective of the model's recorded performance. By doing so, the optimization techniques of the present disclosure may provide an adaptive interface for learning computer efficiencies with respect to continuously changing optimization models and computing environments. These flexibilities improve optimization model development, deployment, and use over time as the feedback loop mechanism may be applied to detect performance drifts and other predictive trends for models as the models are used across different computing environments, datasets, and times. Examples of technologically advantageous embodiments of the present disclosure comprise improved optimization techniques, among other aspects of the present disclosure. Other technical improvements and advantages may be realized by one of ordinary skill in the art. I. OVERVIEW OF EMBODIMENTS As should be appreciated, various embodiments of the present disclosure may be implemented as methods, apparatus, systems, computing devices, computing entities, computer program products, and/or the like. As such, embodiments of the present disclosure may take the form of an apparatus, system, computing device, computing entity, and/or the like executing instructions stored on a computer-readable storage medium to perform certa