Granted Patent B2

US 12,346,921 · App. 18/456,111 · Granted Jul 1, 2025

Inventors: Ali Khanafer (Ottawa, CA); Behrouz Haji Soleimani (Ottawa, CA); Sebastien Ouellet (Ottawa, CA); Christopher Wang (Ottawa, CA); Chantal Bisson-Krol (Ottawa, CA); Zhen Lin (Ottawa, CA)

G06Q30/0205G06F18/211G06F18/217G06F18/22G06F18/251G06F18/285G06N20/00

Abstract

Claims (99)

1. A computer-implemented method, comprising:

receiving, by a processor, a first forecast request;

training, by the processor, a plurality of machine learning forecast models on a first portion of a data set;

validating, by the processor, a machine learning forecast model on a second portion of the data set; and

retraining, by the processor, the machine learning forecast model on a sum of the first portion and the second portion of the data set, the data set comprising processed historical data;

forecasting, by the processor, a forecast based on the first forecast request;

receiving, by the processor, a subsequent forecast request;

selecting, by the processor, a machine learning forecast model when:

i) the data set has been updated by a new class of relevant signal data since a previous forecast request; or

ii) the data set has been updated by an amount of new relevant signal data beyond a first threshold since the previous forecast request; or

iii) the machine learning forecast model has degraded;

and

retraining, by the processor, a previously-selected machine learning forecast model when a time interval between successive forecast requests is greater than a second threshold;

using one of the machine learning forecast model selected by the processor and the previously-selected machine learning forecast model for providing first forecast data for a first forecast window, the first forecast data for one or more store locations;

transmitting the first forecast data to a user;

receiving first sales data for the one or more store locations for a second time interval, the second time interval subsequent a first time interval;

determining an error in the first forecast data based on the first forecast data and the first sales data;

removing the error from the first forecast data for forming first adjusted forecast data, the first adjusted forecast data for the one or more store locations; and

transmitting the first adjusted forecast data to the user.

2. The method of claim 1 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining the error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations corresponding thereto.

3. The method of claim 1 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining a percentage error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations and an average percentage error thereof.

4. The method of claim 3 wherein removing the error from the first forecast data for forming the first adjusted forecast data includes removing the average percentage error from the first forecast data for each of the one or more store locations, the first adjusted forecast data includes first adjusted forecast data for each of the one or more store locations.

5. The method of claim 1 further including,

collecting second data for a third time interval, the second data including at least the historical data and the first sales data;

generating second feature data based on the second data;

processing second feature data by the processor for training a machine learning algorithm for forming a second forecast model;

using the second forecast model for providing second forecast data for a second forecast window, the second forecast data including second forecast data for the one or more store locations; and

transmitting the second forecast data to the user.

6. The method of claim 1 further includes,

receiving second sales data, the second sales data for the one or more store locations during a fourth time interval subsequent the second time interval;

determining an error in the first forecast data based on the first forecast data and the second sales data;

removing an error from the first forecast data for forming third forecast data; and

transmitting the third forecast data to the user.

7. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:

receive, by a processor, a first forecast request;

train, by the processor, a plurality of machine learning forecast models on a first portion of a data set;

validate, by the processor, a machine learning forecast model on a second portion of the data set; and

retrain, by the processor, the machine learning forecast model on a sum of the first portion and the second portion of the data set, the data set comprising processed historical data;

forecast, by the processor, a forecast based on the first forecast request;

receive, by the processor, a subsequent forecast request;

select, by the processor, a machine learning forecast model when:

i) the data set has been updated by a new class of relevant signal data since a previous forecast request; or

ii) the data set has been updated by an amount of new relevant signal data beyond a first threshold since the previous forecast request; or

iii) the machine learning forecast model has degraded; and

retrain, by the processor, a previously-selected machine learning forecast model when a time interval between successive forecast requests is greater than a second threshold;

using one of the machine learn forecast model selected by the processor and the previously-selected machine learning forecast model for providing first forecast data for a first forecast window, the first forecast data for one or more store locations;

transmit the first forecast data to a user;

receive first sales data for the one or more store locations for a second time interval, the second time interval subsequent a first time interval;

determine an error in the first forecast data based on the first forecast data and the first sales data;

remove the error from the first forecast data for forming first adjusted forecast data, the first adjusted forecast data for the one or more store locations; and

transmit the first adjusted forecast data to the user.

8. The computer-readable storage medium of claim 7 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining the error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations corresponding thereto.

9. The computer-readable storage medium of claim 7 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining a percentage error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations and an average percentage error thereof.

10. The computer-readable storage medium of claim 9 wherein removing the error from the first forecast data for forming the first adjusted forecast data includes removing the average percentage error from the first forecast data for each of the one or more store locations, the first adjusted forecast data includes first adjusted forecast data for each of the one or more store locations.

11. The computer-readable storage medium of claim 7 including instructions that when executed by a computer further causes the computer to:

collect second data for a third time interval, the second data including at least the historical data and the first sales data;

generate second feature data based on the second data;

process second feature data by the processor for training a machine learning algorithm for forming a second forecast model;

using the second forecast model for providing second forecast data for a second forecast window, the second forecast data include second forecast data for the one or more store locations; and

transmit the second forecast data to the user.

12. The computer-readable storage medium of claim 7 including instructions that when executed by a computer further causes the computer to:

receive second sales data, the second sales data for the one or more store locations during a fourth time interval subsequent the second time interval;

determine an error in the first forecast data based on the first forecast data and the second sales data;

remove an error from the first forecast data for forming third forecast data; and

transmit the third forecast data to the user.

13. A system comprising:

a processor; and

a memory storing instructions that, when executed by the processor, configure the system to:

receive, by the processor, a first forecast request;

train, by the processor, a plurality of machine learning forecast models on a first portion of a data set;

validate, by the processor, a machine learning forecast model on a second portion of the data set; and

retrain, by the processor, the machine learning forecast model on a sum of the first portion and the second portion of the data set, the data set comprising processed historical data;

forecast, by the processor, a forecast based on the first forecast request;

receive, by the processor, a subsequent forecast request;

select, by the processor, a machine learning forecast model when:

i) the data set has been updated by a new class of relevant signal data since a previous forecast request; or

ii) the data set has been updated by an amount of new relevant signal data beyond a first threshold since the previous forecast request; or

iii) the machine learning forecast model has degraded; and

retrain, by the processor, a previously-selected machine learning forecast model when a time interval between successive forecast requests is greater than a second threshold;

using one of the machine learn forecast model selected by the processor and the previously-selected machine learning forecast model for providing first forecast data for a first forecast window, the first forecast data for one or more store locations;

transmit the first forecast data to a user;

receive first sales data for the one or more store locations for a second time interval, the second time interval subsequent a first time interval;

determine an error in the first forecast data based on the first forecast data and the first sales data;

remove the error from the first forecast data for forming first adjusted forecast data, the first adjusted forecast data for the one or more store locations; and

transmit the first adjusted forecast data to the user.

14. The system of claim 13 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining the error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations corresponding thereto.

15. The system of claim 13 wherein determining the error in the first forecast data based on the first forecast data and the first sales data includes determining a percentage error between the first forecast data for each of the one or more store locations and the first sales data for each of the one or more store locations and an average percentage error thereof.

16. The system of claim 15 wherein removing the error from the first forecast data for forming the first adjusted forecast data includes removing the average percentage error from the first forecast data for each of the one or more store locations, the first adjusted forecast data includes first adjusted forecast data for each of the one or more store locations.

17. The system of claim 13 further configured to:

collect second data for a third time interval, the second data including at least the historical data and the first sales data;

generate second feature data based on the second data;

process second feature data by the processor for training a machine learning algorithm for forming a second forecast model;

using the second forecast model for providing second forecast data for a second forecast window, the second forecast data include second forecast data for the one or more store locations; and

transmit the second forecast data to the user.

18. The system of claim 13 further configured to:

receive second sales data, the second sales data for the one or more store locations during a fourth time interval subsequent the second time interval;

determine an error in the first forecast data based on the first forecast data and the second sales data;

remove an error from the first forecast data for forming third forecast data; and

transmit the third forecast data to the user.

Assignments (1)

Continuity (5)

References Cited (133)