# US 2025/0095016 A1 · Systems and method to facilitate modeling responses to variable values

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0095016 A1
- Document ID: US20250095016A1
- Status: Published application
- Kind: A1
- Application number: 18/884,297
- Filed: 2024-09-13
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: Walmart Apollo, LLC
- Applicants: Walmart Apollo, LLC
- Inventors: Pingjian Yu; Jianbo Gu; Wenyue Shi; Siddharth Hareendran; Yunus Kamal; Pawan R. Natarajan; Philippe E. Bled; Chinar Potnis
- Web page: https://patentgrep.com/patent/US20250095016A1

## CPC

- G06Q 30/0206: {Price or cost determination based on market factors}
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

This disclosure provides techniques for facilitating modeling responses to variable parameters, and in particular embodiments, within the context of a price setting strategy for a retail club. A trained member response metric model may be trained using a training corpus. A modified price for a target item may be then be predicted, and used to calculate a predicted demand for the target item. The predicted demand may be used to calculate predicted sales of the target item, after which predict a member response metric score associated with the modified price may be determined using the first trained member response metric model and the predicted sales.

## Claims

### Claim 1

A system to facilitate modeling responses to variable parameters, the system comprising:
a memory having a dataset stored therein;
a control circuit operably coupled to the memory and configured to:
generate a first trained member response metric model using a first training corpus that includes data from the dataset;
determine a modified price for a target item;
calculate a predicted demand for the target item based the modified price for the target item;
calculate predicted sales of the target item based on the predicted demand; and
predict a member response metric score associated with the modified price using the first trained member response metric model and the predicted sales, the member response metric score indicating a value representing a member's intent to renew a membership to a retail club.

### Claim 2 (depends on 1)

The system of claim 1, wherein the first training corpus includes month-level member transaction feature data.

### Claim 3 (depends on 2)

The system of claim 2, wherein the month-level member transaction feature data comprise any one or more of:
sale data;
saving data;
diversity index of item category;
diversity index of visit;
similarity between consecutive months;
number of months from a last visit;
return rate;
online rate;
self-checkout rate;
application rate;
club pick-up rate; and
fuel rate.

### Claim 4 (depends on 1)

The system of claim 1, wherein the first training corpus includes membership renewal data.

### Claim 5 (depends on 1)

The system of claim 1, wherein the first training corpus includes statistical data of a geographical region associated with the retail club.

### Claim 6 (depends on 1)

The system of claim 1, wherein the first training corpus includes relative price index level data for the retail club.

### Claim 7 (depends on 1)

The system of claim 1, wherein the first trained member response metric model is based on a supervised logistic regression algorithm.

### Claim 8 (depends on 1)

The system of claim 1, wherein the control circuit is further configured to:
generate one or more trained behavior models using a second training corpus, wherein the predicted demand is further determined using the one or more trained behavior models.

### Claim 9 (depends on 8)

The system of claim 8, wherein the second training corpus comprises any one or more of:
information regarding a region of a club;
information regarding demo schedule;
information regarding out of stock status;
information regarding a plurality of related item pairs for each of a plurality of items;
information regarding units and prices of items sold;
information regarding time of transactions; and
traffic information.

### Claim 10 (depends on 8)

The system of claim 8, wherein the one or more trained behavior models are each based on a linear regression algorithm.

### Claim 11 (depends on 1)

The system of claim 1, wherein the control circuit is further configured to:
generate a basic elasticity model and a cross elasticity model using a second training corpus, wherein the predicted demand is further determined using the basic elasticity model;
determine predicted demands for related items using the cross elasticity model and the modified price for the target item; and
integrate the predicted demand of the target item with the predicted demands for the related items.

### Claim 12 (depends on 11)

The system of claim 11, wherein the related items are complementary items of the target item.

### Claim 13 (depends on 11)

The system of claim 11, wherein the related items are substitute items of the target item.

### Claim 14

A method comprising:
generating a first trained member response metric model using a first training corpus that includes data from a dataset;
determining a modified price for a target item;
calculating a predicted demand for the target item based the modified price for the target item;
calculating predicted sales of the target item based on the predicted demand; and
predicting a member response metric score associated with the modified price using the first trained member response metric model and the predicted sales, the member response metric score indicating a value representing a member's intent to renew a membership to a retail club.

### Claim 15 (depends on 14)

The method of claim 14, wherein the first training corpus includes month-level member transaction feature data.

### Claim 16 (depends on 15)

The method of claim 15, wherein the month-level member transaction feature data comprise any one or more of:
sale data;
saving data;
diversity index of item category;
diversity index of visit;
similarity between consecutive months;
number of months from a last visit;
return rate;
online rate;
self-checkout rate;
application rate;
club pick-up rate; and
fuel rate.

### Claim 17 (depends on 14)

The method of claim 14, wherein the first training corpus includes membership renewal data.

### Claim 18 (depends on 14)

The method of claim 14, wherein the first training corpus includes statistical data of a geographical region associated with the retail club.

### Claim 19 (depends on 14)

The method of claim 14, wherein the first training corpus includes relative price index level data for the retail club.

### Claim 20 (depends on 14)

The method of claim 14, wherein the first trained member response metric model is based on a supervised logistic regression algorithm.
