System and method for determining trailing data adjustment factors
View Patent ↗Timely projections of product sales for a reporting time period are obtained by combining actual sales data received from reporting stores and estimated sales data for non-reporting stores. The projections are adjusted to account for trailing data, which may be reported after the end of the subject time period.
1. A method comprising:
receiving historical market data for one or more sample outlets;
generating a first preliminary forecast of a product demand for a first time interval, wherein generating the first preliminary forecast comprises:
generating a sample forecast for at least one sample outlet of the one or more sample outlets based on the historical market data, and
for at least one non-sample outlet determining a projection factor and estimating a non-sample forecast using the projection factor;
receiving a first live market data during the first time interval;
screening the first live market data to exclude from subsequent processing a portion of the first live market data corresponding to one or more unusual events;
determining, by one or more processing devices, a first adjustment factor based on a difference between the screened live market data, which excludes the portion of the first live market data corresponding to one or more unusual events, and the first preliminary forecast; and
updating the first preliminary forecast for the first time interval using the first adjustment factor to derive a second preliminary forecast for the first time interval.
2. The method of claim 1 , further comprising:
receiving a second live market data for a second time interval;
screening the second live market data to eliminate data corresponding to one or more unusual events;
calculating a second adjustment factor based on a difference between the second live market data and the second preliminary forecast; and
updating the second preliminary forecast using the second adjustment factor.
3. The method of claim 1 , wherein calculating the first adjustment factor includes determining a trailing data factor.
4. The method of claim 1 , wherein the first adjustment factor is calculated on a product-level.
5. The method of claim 1 , wherein the first live market data indicates data gathered during a time interval that overlaps with the first time interval for the first preliminary forecast.
6. A computer-readable non-transitory storage medium encoded with a computer program, the program comprising instructions that when executed by one or more processors cause the one or more processors to perform operations comprising:
receiving historical market data for one or more sample outlets;
generating a first preliminary forecast of a product demand for a first time interval, wherein generating the first preliminary forecast comprises:
generating a sample forecast for at least one sample outlet of the one or more sample outlets based on the historical market data, and
for at least one non-sample outlet, determining a projection factor and generating a non-sample forecast using the projection factor;
receiving a first live market data during the first time interval;
screening the first live market data to exclude, from subsequent processing, a portion of the first live market data corresponding to one or more unusual events;
calculating a first adjustment factor based on a difference between the screened live market data, which excludes the portion of the first live market data corresponding to one or more unusual events, and the first preliminary forecast; and
updating the first preliminary forecast for the first time interval using the first adjustment factor to derive a second preliminary forecast for the first time interval.
7. The computer-readable medium of claim 6 , further comprising instructions operable to direct the processing unit to perform:
receiving a second live market data for a second time interval;
screening the second live market data to eliminate data corresponding to one or more unusual events;
calculating a second adjustment factor based on a difference between the second live market data and the second preliminary forecast; and
updating the second preliminary forecast using the second adjustment factor.
8. The computer-readable medium of claim 6 , wherein calculating the first adjustment factor includes determining a trailing data factor.
9. The computer-readable medium of claim 6 , wherein the first adjustment factor is calculated on a product-level.
10. The computer-readable medium of claim 6 , wherein the first live market data indicates data gathered during a time interval that overlaps with the first time interval for the first preliminary forecast.
11. A system comprising:
one or more processing devices; and
a non-transitory computer-readable medium coupled to the one or more processing devices having instructions stored thereon which, when executed by the one or more processing devices, cause the one or more processing devices to perform operations comprising:
receiving historical market data for one or more sample outlets;
generating a first preliminary forecast of a product demand for a first time interval, wherein generating the first preliminary forecast comprises:
generating a sample forecast for at least one sample outlet of the one or more sample outlets based on the historical market data, and
for at least one non-sample outlet, determining a projection factor and generating a non-sample forecast using the projection factor;
receiving a first live market data during the first time interval;
screening the first live market data to exclude, from subsequent processing, a portion of the first live market data corresponding to one or more unusual events;
determining a first adjustment factor based on a difference between the screened live market data, which excludes the portion of the first live market data corresponding to one or more unusual events, and the first preliminary forecast; and
updating the first preliminary forecast for the first time interval using the first adjustment factor to derive a second preliminary forecast for the first time interval.
12. The system of claim 11 , wherein the processing arrangement is configured to further perform:
receiving a second live market data for a second time interval;
screening the second live market data to eliminate data corresponding to one or more unusual events;
calculating a second adjustment factor based on a difference between the second live market data and the second preliminary forecast; and
updating the second preliminary forecast using the second adjustment factor.
13. The system of claim 11 , wherein calculating the first adjustment factor includes determining a trailing data factor.
14. The system of claim 11 , wherein the first adjustment factor is calculated on a product-level.
15. The system of claim 11 , wherein the first live market data indicates data gathered during a time interval that overlaps with the first time interval for the first preliminary forecast.
16. The method of claim 1 , wherein determining a first adjustment factor based on a difference between the screened live market data, which excludes the portion of the first live market data corresponding to one or more unusual events, and the preliminary forecast comprises:
calculating a first adjustment factor based on a difference between the screened live market data, which excludes the portion of the first live market data corresponding to one or more unusual events, and the sample forecast that was generated for at least one sample outlet of the one or more sample outlets.