# US 2026/0065303 A1 · Real time trained predictive time series model

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

- Number: US 2026/0065303 A1
- Document ID: US20260065303A1
- Status: Published application
- Kind: A1
- Application number: 18/961,886
- Filed: 2024-11-27
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: NCR Voyix Corporation
- Applicants: NCR Voyix Corporation
- Inventors: Noa Shmulevich; Shiran Abadi
- Web page: https://patentgrep.com/patent/US20260065303A1

## CPC

- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 30/02024: {based on temporal or time series analysis, e.g. seasonality or cyclical}
- 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

System and techniques may be used for generating a predictive time series of sales data. An example technique may include training a generic time series model including a non-symmetric logistic regression to generate a trained model that applies to a particular store by optimizing a parameter of the regression. The technique may include storing the generating predicted cumulative sales data for a first time of a sales day using cumulative sales data, determining a ratio between real cumulative sales at the first time and the predicted cumulative sales at the first time, and modifying the optimized parameter based on the ratio. The technique may include generating updated predicted cumulative sales data for a second time using the modified optimized parameter, and outputting a graph representing the updated predicted cumulative sales data for the second time.

## Claims

### Claim 1

A method comprising:
training a generic time series model including a non-symmetric logistic regression to generate a trained model that applies to a particular store by:
retrieving historical sales data for the particular store; and
optimizing a parameter of the non-symmetric logistic regression;
storing the optimized parameter of the trained model;
receiving a request for an updated sales forecast at a first time of a sales day of the particular store;
generating predicted cumulative sales data for the first time using cumulative sales data of the sales day up to the first time, the optimized parameter, and the trained model;
determining a relationship between real cumulative sales at the first time and the predicted cumulative sales at the first time;
modifying the optimized parameter based on the determined relationship;
generating updated predicted cumulative sales data for a second time using the modified optimized parameter;
rendering a graphical representation of the real cumulative sales at the first time and the updated predicted cumulative sales data for the second time; and
outputting the graphical representation for display on a user interface in response to the request for the updated sales forecast.

### Claim 2 (depends on 1)

The method of claim 1, wherein a left boundary for the non-symmetric logistic regression includes zero sales at a start time of the sales day.

### Claim 3 (depends on 1)

The method of claim 1, wherein the second time is an end of the sales day.

### Claim 4 (depends on 1)

The method of claim 1, wherein the sales day corresponds to hours that the particular store is open.

### Claim 5 (depends on 1)

The method of claim 1, further comprising outputting the updated predicted cumulative sales data as an end-of-day sales forecast.

### Claim 6 (depends on 1)

The method of claim 1, wherein accuracy of generating the updated predicted cumulative sales data is proportional to an amount of time between the first time and the second time.

### Claim 7 (depends on 1)

The method of claim 1, wherein the non-symmetric logistic regression is subject to constraints including:
{
0
x
<
left
boundary
L
*
1
1
+
e
k
*
(
x
-
x
⁢
0
)
+
b
left
boundary
≤
x
≤
right
boundary
L
*
1
1
+
e
k
*
(
right
boundary
-
x
⁢
0
)
+
b
x
≥
right
boundary
where k, L, b, x0, leftboundary, and rightboundary are function parameters that are fitted to prior observed data, and x is a current time of the sales day.

### Claim 8 (depends on 7)

The method of claim 7, wherein modifying the optimized parameter based on the determined relationship includes adjusting L and b based on a ratio between the real cumulative sales at the first time and the predicted cumulative sales at the first time.

### Claim 9 (depends on 8)

The method of claim 8, wherein generating the updated predicted cumulative sales data for the second time using the modified optimized parameter includes using the adjusted L and b.

### Claim 10 (depends on 1)

The method of claim 1, wherein the graphical representation includes actual sales data from a start time of the sales day up to the first time and predicted sales data from the first time to an end of the sales day.

### Claim 11

At least one machine-readable medium including instructions that when executed by processing circuitry cause the processing circuitry to perform operations comprising:
training a generic time series model including a non-symmetric logistic regression to generate a trained model that applies to a particular store by:
retrieving historical sales data for the particular store; and
optimizing a parameter of the non-symmetric logistic regression;
storing the optimized parameter of the trained model;
receiving a request for an updated sales forecast at a first time of a sales day of the particular store;
generating predicted cumulative sales data for the first time using cumulative sales data of the sales day up to the first time, the optimized parameter, and the trained model;
determining a relationship between real cumulative sales at the first time and the predicted cumulative sales at the first time;
modifying the optimized parameter based on the determined relationship;
generating updated predicted cumulative sales data for a second time using the modified optimized parameter;
rendering a graphical representation of the real cumulative sales at the first time and the updated predicted cumulative sales data for the second time; and
outputting the graphical representation for display on a user interface in response to the request for the updated sales forecast.

### Claim 12 (depends on 11)

The at least one machine-readable medium of claim 11, wherein a left boundary for the non-symmetric logistic regression includes zero sales at a start time of the sales day.

### Claim 13 (depends on 11)

The at least one machine-readable medium of claim 11, wherein the second time is an end of the sales day.

### Claim 14 (depends on 11)

The at least one machine-readable medium of claim 11, wherein the sales day corresponds to hours that the particular store is open.

### Claim 15 (depends on 11)

The at least one machine-readable medium of claim 11, further comprising outputting the updated predicted cumulative sales data as an end-of-day sales forecast.

### Claim 16 (depends on 11)

The at least one machine-readable medium of claim 11, wherein accuracy of generating the updated predicted cumulative sales data is proportional to an amount of time between the first time and the second time.

### Claim 17 (depends on 11)

The at least one machine-readable medium of claim 11, wherein the non-symmetric logistic regression is subject to constraints including:
{
0
x
<
left
boundary
L
*
1
1
+
e
k
*
(
x
-
x
⁢
0
)
+
b
left
boundary
≤
x
≤
right
boundary
L
*
1
1
+
e
k
*
(
right
boundary
-
x
⁢
0
)
+
b
x
≥
right
b
⁢
o
⁢
u
⁢
n
⁢
d
⁢
a
⁢
r
⁢
y
where k, L, b, x0, leftboundary, and rightboundary are function parameters that are fitted to prior observed data, and x is a current time of the sales day.

### Claim 18 (depends on 17)

The at least one machine-readable medium of claim 17, wherein modifying the optimized parameter based on the determined relationship includes adjusting L and b based on a ratio between the real cumulative sales at the first time and the predicted cumulative sales at the first time.

### Claim 19 (depends on 18)

The at least one machine-readable medium of claim 18, wherein generating the updated predicted cumulative sales data for the second time using the modified optimized parameter includes using the adjusted L and b.

### Claim 20 (depends on 11)

The at least one machine-readable medium of claim 11, wherein the graphical representation includes actual sales data from a start time of the sales day up to the first time and predicted sales data from the first time to an end of the sales day.
