Multi-locational forecast modeling in both temporal and spatial dimensions

Patent metadata

Field	Value
Publication number	US-12423487-B2
Application number	US-202117458728-A
Country	US
Kind code	B2
Filing date	Aug 27, 2021
Priority date	Aug 27, 2021
Publication date	Sep 23, 2025
Grant date	Sep 23, 2025

Abstract

Temporal and spatially integrated forecast modeling includes generating a plurality of forecast models for a plurality of short-term to long-term time periods for a plurality of locations. Temporally integrating the plurality of forecast models sequentially over the plurality of time periods for the plurality of locations and spatially integrating the temporally integrated plurality of forecast models for each location hierarchically over the geographic areas. The forecast models are autoregressive distributed lag models with different explanatory variables for the short-term and long-term forecast models. The temporally integrating includes recursively integrating the plurality of forecast models over the time periods from the short-term to the long-term time periods and the spatially integrating includes recursively integrating the temporally integrated plurality of forecast models hierarchically from larger size geographic areas to smaller size geographic areas. The method includes optimizing the resultant spatially and temporally integrated forecast model based on a plurality of constraints.

First claim

What is claimed is:

1. A computer implemented forecast modeling method comprising:
generating a plurality of forecast models for a plurality of time periods, the time periods including short-term and long-term time periods, each forecast model of the plurality of forecast models being for a different time period for a plurality of geographic locations, the geographic locations including a plurality of geographic areas grouped hierarchically based the geographic size of the geographic areas;
temporally integrating the plurality of forecast models sequentially over the plurality of time periods for the plurality of locations; and
spatially integrating, by executing program instructions on a computer, the temporally integrated plurality of forecast models for each geographic location hierarchically over the geographic areas to generate a resultant spatially and temporally integrated forecast model;
generating, by the resultant spatially and temporally integrated forecast model, forecasting results in both the temporal and spatial dimensions; and
displaying the forecasting results comprising forecasts for all of the plurality of geographic locations for each of the short-term and long-term time periods.

2. The computer implemented method of claim 1 , wherein the plurality of forecast models are generated based on a set variables in an autoregressive distributed lag model.

3. The computer implemented method of claim 2 , wherein the set of variables includes a first set variables for the short-term forecast models and a second set variables different from the first set for the long-term forecast models.

4. The computer implemented method of claim 1 , wherein the temporally integrating comprises recursively integrating the plurality of forecast models over the time periods from the short-term to the long-term time periods.

5. The computer implemented method of claim 1 , wherein the spatially integrating comprises recursively integrating the temporally integrated plurality of forecast models hierarchically from larger size geographic areas to smaller size geographic areas.

6. The computer implemented method of claim 1 , further comprising automatically synchronizing the forecast results in the spatial and temporal dimensions, such that any forecast changes in any level from short-term to long-term, from local to global, the resultant spatially and temporally integrated forecast model will reflect such changes.

7. The computer implemented method of claim 1 , further comprising optimizing the resultant spatially and temporally integrated forecast model based on a plurality of constraints.

8. A computer system for forecast modeling, comprising:
one or more computer processors;
one or more non-transitory computer-readable storage media;
program instructions, stored on the one or more non-transitory computer-readable storage media, which when implemented by the one or more processors, cause the computer system to perform the steps of:
generating a plurality of forecast models for a plurality of time periods, the time periods including short-term and long-term time periods, each forecast model of the plurality of forecast models being for a different time period for a plurality of geographic locations, the geographic locations including a plurality of geographic areas grouped hierarchically based the geographic size of the geographic areas;
temporally integrating the plurality of forecast models sequentially over the plurality of time periods for the plurality of locations; and
spatially integrating, by executing program instructions on a computer, the temporally integrated plurality of forecast models for each geographic location hierarchically over the geographic areas to generate a resultant spatially and temporally integrated forecast model;
generating, by the resultant spatially and temporally integrated forecast model, forecasting results in both the temporal and spatial dimensions; and
displaying the forecasting results comprising forecasts for all of the plurality of geographic locations for each of the short-term and long-term time periods.

9. The computer system of claim 8 , wherein the plurality of forecast models are generated based on a set variables in an autoregressive distributed lag model.

10. The computer system of claim 9 , wherein the set of variables includes a first set variables for the short-term forecast models and a second set variables different from the first set for the long-term forecast models.

11. The computer system of claim 8 , wherein the temporally integrating comprises recursively integrating the plurality of forecast models over the time periods from the short-term to the long-term time periods.

12. The computer system of claim 8 , wherein the spatially integrating comprises recursively integrating the temporally integrated plurality of forecast models hierarchically from larger size geographic areas to smaller size geographic areas.

13. The computer system of claim 8 , further comprising automatically synchronizing the forecast results in the spatial and temporal dimensions, such that any forecast changes in any level from short-term to long-term, from local to global, the resultant spatially and temporally integrated forecast model will reflect such changes.

14. The computer system of claim 8 , further comprising optimizing the resultant spatially and temporally integrated forecast model based on a plurality of constraints.

15. A computer program product comprising:
program instructions on a computer-readable storage medium, where execution of the program instructions using a computer causes the computer to perform a method for forecast modeling, comprising:
generating a plurality of forecast models for a plurality of time periods, the time periods including short-term and long-term time periods, each forecast model of the plurality of forecast models being for a different time period for a plurality of geographic locations, the geographic locations including a plurality of geographic areas grouped hierarchically based the geographic size of the geographic areas;
temporally integrating the plurality of forecast models sequentially over the plurality of time periods for the plurality of locations; and
spatially integrating, by executing program instructions on a computer, the temporally integrated plurality of forecast models for each geographic location hierarchically over the geographic areas to generate a resultant spatially and temporally integrated forecast model;
generating, by the resultant spatially and temporally integrated forecast model, forecasting results in both the temporal and spatial dimensions; and
displaying the forecasting results comprising forecasts for all of the plurality of geographic locations for each of the short-term and long-term time periods.

16. The computer program product of claim 15 , wherein the plurality of forecast models are generated based on a set variables in an autoregressive distributed lag model, and wherein the set of variables includes a first set variables for the short-term forecast models and a second set variables different from the first set for the long-term forecast models.

17. The computer program product of claim 15 , further comprising automatically synchronizing the forecast results in the spatial and temporal dimensions, such that any forecast changes in any level from short-term to long-term, from local to global, the resultant spatially and temporally integrated forecast model will reflect such changes.

18. The computer program product of claim 15 , wherein the

Assignees

• IBM

Inventors

• Xue Zhengliang
• Agrawal Bhavna
• Bhamidipaty Anuradha
• Li Yingjie
• Lin Shuxin

Classifications

• G06F2111/04

  Constraint-based CAD · CPC title

• G06Q40/06

  Asset management; Financial planning or analysis · CPC title

• G06F2111/10

  Numerical modelling · CPC title

• G06F30/20 Primary

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title