Back to results
US 2023/0401592 A1Published application
Systems and methods for dynamic demand sensing and forecast adjustment
OwnerAli KHANAFER, Behrouz Haji SOLEIMANI +4inventors
InventorsAli KHANAFER, Behrouz Haji SOLEIMANI, Sebastien OUELLET, Christopher WANG, Chantal BISSON-KROL, Zhen LIN
Life of this patent
Estimating the term…
Abstract
Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information. Also disclosed are systems and methods relating to demand forecasting and readjusting forecasts based on forecast error.
Claims18
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.
19 more elements
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.
19 more elements
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.
22 more elements
Dependencies are inferred from the claim text.