Granted Patent B2

US 12,511,661 · App. 17/537,367 · Granted Dec 30, 2025

Inventors: Levon J. Lloyd (Secaucus, NJ); Nader Al-Naji (New York, NY); Matthew Ivor Lloyd (Long Island City, NY)

Assignee: Block, Inc.

G06Q30/0202G06Q30/0201G06Q30/0205

Abstract

Claims (88)

1 . A computer-implemented method comprising:

receiving, by one or more servers of a service provider providing a plurality of merchant services and from a point-of-sale (POS) device, first transaction data associated with a plurality of first payment transactions processed on behalf of a merchant;

applying, by the one or more servers, a model having a core set of features for predicting a merchant metric associated with the merchant, wherein the model is based at least in part on the first transaction data associated with the plurality of first payment transactions;

detecting, by the one or more servers, a change in an observed value of the merchant metric based at least in part on a change between the first transaction data and subsequent transaction data associated with a plurality of second payment transactions;

determining, by the one or more servers, one or more features associated with the change in the observed value;

modifying, by the one or more servers, the core set of features of the model to cause the observed value of the merchant metric to correspond to a predicted value of the merchant metric;

generating, by the one or more servers, personalized content for the merchant based at least in part on the change in the observed value, wherein the personalized content comprises at least one of a recommendation to change a business practice of the merchant or an offer to provision a merchant service of the plurality of merchant services;

responsive to generating the personalized content, configuring, by the one or more servers, one or more graphical user interfaces (GUIs) including the personalized content comprising one or more interactable elements associated with the at least one of the recommendation or the offer;

causing, by the one or more servers, presentation of the one or more GUIs on the POS device;

receiving, by the one or more servers, an indication of an interaction with a first interactable element of a first GUI of the one or more GUIs; and

responsive to receiving the indication of the interaction, causing, by the one or more servers, presentation of a second GUI of the one or more GUIs that includes a time series forecast for the merchant metric based on the modified core set of features and a second interactive element.

2 . The computer-implemented method of claim 1 , wherein the core set of features represent a first core set of features, and the computer-implemented method further comprising:

associating the merchant with a merchant profile based at least in part on the first transaction data;

associating the merchant profile with at least one merchant category of a plurality of different merchant categories, wherein the plurality of different merchant categories are based at least in part on at least one of: a geographic region, an item offered for sale, or a buyer demographic, wherein the one or more features associated with the change in the observed value includes a feature based at least in part on the at least one merchant category;

applying a merchant specific model for the merchant profile based at least in part on a subset of the first transaction data associated with the merchant profile, wherein the merchant specific model has a second core set of features;

applying a category specific model based at least in part on the first transaction data associated with a plurality of other merchant profiles in a same merchant category as the merchant profile, wherein the category specific model has a third core set of features; and

applying the model as a weighted combination of the merchant specific model and the category specific model.

3 . The computer-implemented method of claim 2 , wherein the personalized content comprises the recommendation, and wherein the recommendation includes at least one of: an inventory suggestion, an employee scheduling suggestion, or an hours of operation suggestion.

4 . The computer-implemented method of claim 1 , further comprising determining, for an individual feature of the core set of features, a degree to which the individual feature contributes to a variance of the model.

5 . The computer-implemented method of claim 1 , wherein the personalized content comprises the recommendation, the computer-implemented method further comprising:

determining a plurality of recommendations associated with the change in the observed value for the merchant; and

ranking the plurality of recommendations based at least in part on a degree to which individual features of the plurality of recommendations contribute to variance of the model,

wherein the recommendation comprises at least a highest ranked recommendation.

6 . The computer-implemented method of claim 1 , wherein the time series forecast comprises a first time series forecast, the computer-implemented method further comprising:

receiving event data from a content source, wherein the event data includes at least one of weather information, an event calendar, or financial data;

determining a prospective feature included in the event data, wherein the prospective feature includes at least one parameter;

generating a second time series forecast to represent the at least one parameter of the prospective feature; and

incorporating the second time series forecast into the model to cause observed values of the merchant metric over a period of time to correspond to the predicted value.

7 . The computer-implemented method of claim 1 , wherein the model represents a first merchant specific model associated with the merchant, the change in the observed value represents a first change in the observed value, the one or more features represent one or more first features, and the computer-implemented method further comprising:

applying a plurality of merchant specific models associated with a plurality of respective other merchants, wherein the plurality of merchant specific models are based at least in part on transaction data associated with the plurality of respective other merchants, and wherein the plurality of merchant specific models have the core set of features;

detecting a group of changes in the first merchant specific model and a subset of the plurality of merchant specific models with respect to observed values of the merchant metric;

determining that a database of features does not include a second feature associated with the group of changes;

determining at least one parameter associated with the group of changes, wherein the at least one parameter includes at least one of a date or a time value associated with the first change;

generating a third feature, within the database of features, representing the at least one parameter associated with the group of changes; and

incorporating the third feature into the first merchant specific model.

8 . The computer-implemented method of claim 1 ,

wherein the model is further based at least in part on at least one of foot traffic data, employee performance, employee scheduling, product inventory, product return information, customer data, marketing expenses, marketing promotion, or shelf space allocation,

wherein the core set of features includes at least one of: a day of a week, historic sales data, seasonal information, geographic location, local weather data, economic health, a local holiday calendar, or a local event calendar, and

wherein the merchant metric includes at least one of: sales of an item, sales at one or more point-of-sale (POS) locations associated with a merchant profile, or gross sales.

9 . The computer-implemented method of claim 1 , wherein the personalized content comprises a plurality of recommendations and a plurality of offers, wherein the first GUI includes a plurality of panels, wherein a first panel of the plurality of panels includes the plurality of recommendations, wherein a second panel of the plurality of panels includes the plurality of offers.

10 . The computer-implemented method of claim 9 , wherein the first GUI further includes a third panel of the plurality of panels, and wherein the third panel displays one or more explanations for the change in the observed value.

11 . The computer-implemented method of claim 10 , wherein an individual explanation of the one or more explanations corresponds to an individual recommendation in the first panel.

12 . The computer-implemented method of claim 11 , wherein the individual explanation of the one or more explanations further corresponds to an individual offer of the plurality of offers.

13 . A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions cause the one or more processors to perform acts comprising:

receiving, by one or more servers of a service provider providing a plurality of merchant services and from a point-of-sale (POS) device, first transaction data associated with a plurality of first payment transactions processed on behalf of a merchant;

applying, by the one or more servers, a model having a core set of features for predicting a merchant metric associated with the merchant, wherein the model is based at least in part on the first transaction data associated with the plurality of first payment transactions;

detecting, by the one or more servers, a change in an observed value of the merchant metric based at least in part on a change between the first transaction data and subsequent transaction data associated with a plurality of second payment transactions;

determining, by the one or more servers, one or more features associated with the change in the observed value;

modifying, by the one or more servers, the core set of features of the model to cause the observed value of the merchant metric to correspond to a predicted value of the merchant metric;

generating, by the one or more servers, personalized content for the merchant based at least in part on the change in the observed value, wherein the personalized content comprises at least one of a recommendation to change a business practice of the merchant or an offer to provision a merchant service of the plurality of merchant services;

responsive to generating the personalized content, configuring, by the one or more servers, one or more graphical user interfaces (GUIs) including the personalized content comprising one or more interactable elements associated with the at least one of the recommendation or the offer;

causing, by the one or more servers, presentation of the one or more GUIs on the POS device;

receiving, by the one or more servers, an indication of an interaction with a first interactable element of a first GUI of the one or more GUIs; and

responsive to receiving the indication of the interaction, causing, by the one or more servers, presentation of a second GUI of the one or more GUIs that includes a time series forecast for the merchant metric based on the modified core set of features and a second interactive element.

14 . The system of claim 13 , wherein the core set of features represent a first core set of features, and the acts further comprising:

associating the merchant with a merchant profile based at least in part on the first transaction data;

associating the merchant profile with at least one merchant category of a plurality of different merchant categories, wherein the plurality of different merchant categories are based at least in part on at least one of: a geographic region, an item offered for sale, or a buyer demographic;

applying a merchant specific model for the merchant profile based at least in part on a subset of the first transaction data associated with the merchant profile, wherein the merchant specific model has a second core set of features;

applying a category specific model based at least in part on the first transaction data associated with a plurality of other merchant profiles in a same merchant category as the merchant profile, wherein the category specific model has a third core set of features; and

applying the model as a weighted combination of the merchant specific model and the category specific model.

15 . One or more non-transitory computer-readable media storing instructions executable by one or more processors that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:

receiving, by one or more servers of a service provider providing a plurality of merchant services and from a point-of-sale (POS) device, first transaction data associated with a plurality of first payment transactions processed on behalf of a merchant;

applying, by the one or more servers, a model having a core set of features for predicting a merchant metric associated with the merchant, wherein the model is based at least in part on the first transaction data associated with the plurality of first payment transactions;

detecting, by the one or more servers, a change in an observed value of the merchant metric based at least in part on a change between the first transaction data and subsequent transaction data associated with a plurality of second payment transactions;

determining, by the one or more servers, one or more features associated with the change in the observed value;

modifying, by the one or more servers, the core set of features of the model to cause the observed value of the merchant metric to correspond to a predicted value of the merchant metric;

generating, by the one or more servers, personalized content for the merchant based at least in part on the change in the observed value, wherein the personalized content comprises at least one of a recommendation to change a business practice of the merchant or an offer to provision a merchant service of the plurality of merchant services;

responsive to generating the personalized content, configuring, by the one or more servers, one or more graphical user interfaces (GUIs) including the personalized content comprising one or more interactable elements associated with the at least one of the recommendation or the offer;

causing, by the one or more servers, presentation of the one or more GUIs on the POS device;

receiving, by the one or more servers, an indication of an interaction with a first interactable element of a first GUI of the one or more GUIs; and

responsive to receiving the indication of the interaction, causing, by the one or more servers, presentation of a second GUI of the one or more GUIs that includes a time series forecast for the merchant metric based on the modified core set of features and a second interactive element.

16 . The one or more non-transitory computer-readable media of claim 15 , the acts further comprising determining, for an individual feature of the core set of features, a degree to which the individual feature contributes to a variance of the model.

17 . The one or more non-transitory computer-readable media of claim 15 , wherein the personalized content comprises the recommendation, the acts further comprising:

determining a plurality of recommendations associated with the change in the observed value for the merchant; and

ranking the plurality of recommendations based at least in part on a degree to which individual features of the plurality of recommendations contribute to variance of the model,

wherein the recommendation comprises at least a highest ranked recommendation.

18 . The one or more non-transitory computer-readable media of claim 15 , wherein the model represents a first merchant specific model associated with the merchant, the change in the observed value represents a first change in the observed value, the one or more features represent one or more first features, and the acts further comprising:

applying a plurality of merchant specific models associated with a plurality of respective other merchants, wherein the plurality of merchant specific models are based at least in part on transaction data associated with the plurality of respective other merchants, and wherein the plurality of merchant specific models have the core set of features;

detecting a group of changes in the first merchant specific model and a subset of the plurality of merchant specific models with respect to observed values of the merchant metric;

determining that a database of features does not include a second feature associated with the group of changes;

determining at least one parameter associated with the group of changes, wherein the at least one parameter includes at least one of a date or a time value associated with the first change;

generating a third feature, within the database of features, representing the at least one parameter associated with the group of changes; and

incorporating the third feature into the first merchant specific model.

19 . The one or more non-transitory computer-readable media of claim 15 , the acts further comprising:

facilitating, by the one or more servers, an action associated with the recommendation or the offer.

20 . The one or more non-transitory computer-readable media of claim 15 , wherein the plurality of merchant services includes one or more of marketing services, financial services, or employment services.

Assignments (2)

Continuity (3)

References Cited (83)