Forecasting a time series based on actuals and a plan

Patent metadata

Field	Value
Publication number	US-10395198-B2
Application number	US-201314046852-A
Country	US
Kind code	B2
Filing date	Oct 4, 2013
Priority date	Oct 4, 2013
Publication date	Aug 27, 2019
Grant date	Aug 27, 2019

Abstract

Embodiments of the present invention provide a system, method and computer program product for forecasting a time series based on actuals and a plan. A method comprises generating a first and a second sequence of segments that rise and fall alternately based on a first and a second sequence of data values over time, respectively. The first and second sequence of data values represent actual data for an ongoing project and estimated data for a planned project, respectively. The method further comprises aligning at least one segment of the second sequence of segments with at least one segment of the first sequence of segments, and adjusting the estimated data by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments. The scaled version maintains an estimated total for the planned project.

First claim

What is claimed is:

1. A method, comprising:
at a ledger storage unit:
recording historical ledger data, wherein the historical ledger data comprises a first sequence of actual costs incurred by an ongoing project over time;

at a cost cases storage unit:
recording one or more cost cases, wherein the one or more cost cases comprises a second sequence of cost estimations for a planned project over time;

at a pre-processing device including at least one hardware processor:
retrieving the historical ledger data from the ledger storage unit;
constructing a typical model based on the historical ledger data;
constructing a generic model for the ongoing project by extrapolating the first sequence of actual costs into the future, wherein the extrapolating comprises adding a scaled version of the typical model to an end of the fist sequence of actual costs;
retrieving the second sequence of cost estimations from the cost cases storage unit;
constructing an estimate model for the planned project based on the second sequence of cost estimations; and
aligning and re-shaping the estimate model based on actual costs included in the historical ledger data, wherein the estimate model is maintained on a models storage unit;

at a training device including at least one hardware processor:
retrieving the estimate model from the models storage unit; and
forecasting long-range cost estimations for the planned project based on the estimate model and the generic model, wherein the long-range cost estimations are maintained on a predictions storage unit, and the long-range cost estimations represent cost estimations for the planned project up to an end date scheduled in the future; and

at a display device including at least one hardware processor:
displaying an interactive user interface; and
reporting forecasting results for the planned project via the interactive user interface, wherein the forecasting results is based on read-only, pre-indexed data maintained on a reporting storage unit and extracted from the estimate model maintained on the models storage unit and the long-range cost estimations maintained on the predictions storage unit;

wherein at least one of the historical ledger data and the one or more cost cases is updated on a periodic basis.

2. The method of claim 1 , wherein aligning and re-shaping the estimate model based on actual costs included in the historical ledger data comprises:
generating a first sequence of segments that rise and fall alternately based on the first sequence of actual costs, wherein the first sequence of segments comprises at least one rising segment that rises to a peak data value of the first sequence of actual costs and at least one falling segment that falls to a trough data value of the first sequence of actual costs;
generating a second sequence of segments that rise and fall alternately based on the second sequence of cost estimations, wherein the second sequence of segments comprises at least one rising segment that rises to a peak data value of the second sequence of cost estimations and at least one falling segment that falls to a trough data value of the second sequence of cost estimations;
aligning at least one segment of the second sequence of segments with at least one corresponding segment of the first sequence of segments at a first point of alignment, wherein the first point of alignment is one of a peak data value or a trough data value of the first sequence of actual costs; and
concatenating the second sequence of segments with the first sequence of segments by replacing at least one segment of the second sequence of segments with a scaled version of at least one corresponding aligned segment of the first sequence of segments to extrapolate one or more additional data values from the second sequence of cost estimations, wherein the scaled version is based on a scaling factor that maintains an estimated total cost for the planned project.

3. The method of claim 2 , wherein:
the one or more additional data values comprises one or more past data values; and
the first point of alignment occurs after the one or more additional data values.

4. The method of claim 2 , wherein:
the one or more additional data values comprises one or more future data values; and
the first point of alignment occurs before the one or more additional data values.

5. The method of claim 2 , wherein:
the scaling factor comprises a ratio between an actual total cost for the ongoing project and the estimated total cost for the planned project.

6. The method of claim 2 , wherein:
each peak data value of the first sequence of actual costs:
is greater than a data value immediately preceding the peak data value; and
is no less than a first subset and a second subset of data values immediately preceding and immediately following the peak data value, respectively, and at least one of the first and the second subset of data values comprises a contiguous subsequence of at least two data values; and

each trough data value of the first sequence of actual costs:
is less than a data value immediately preceding the trough data value; and

is no greater than a third subset and a fourth subset of data values immediately preceding and immediately following the trough data value, respectively, and at least one of the third and the fourth subset of data values comprises a contiguous subsequence of at least two data values.

7. The method of claim 2 , wherein:
each peak data value of the second sequence of cost estimations:
is greater than a data value immediately preceding the peak data value; and
is no less than a first subset and a second subset of data values immediately preceding and immediately following the peak data value, respectively, and at least one of the first and the second subset of data values comprises a contiguous subsequence of at least two data values; and

each trough cost value of the second sequence of cost estimations:
is less than a data value immediately preceding the trough data value; and
is no greater than a third subset and a fourth subset of data values immediately preceding and immediately following the trough data value, respectively, and at least one of the third and the fourth subset of data values comprises a contiguous subsequence of at least two data values.

8. The method of claim 1 , wherein:
each project is a service delivery project; and
the method further comprises:
filtering the forecasting results based on a business domain; and
aggregating the forecasting results based on a sector or customer.

9. A method, comprising:
at a ledger storage unit:
recording historical ledger data, wherein the historical ledger data comprises a first sequence of actual costs incurred by an ongoing service delivery project over time;

at a cost cases storage unit:
recording one or more cost cases, wherein the one or more cost cases comprises a second sequence of cost estimations for a planned service delivery project over time;

at a pre-processing device including at least one hardware processor:
retrieving the historical ledger data from the ledger storage unit;
constructing a typical model based on the historical ledger data;
constructing a generic model for the ongoing service delivery project by extrapolating the first sequence of actual costs into the future, wherein the extrapolating comprises adding a scaled version of the typical model to an end of the fist sequence of actual costs;
retrieving the second sequence of cost estimations from the cost cases storage unit;
constructing an estimate model for the planned service delivery project based on the second sequence of cost estimations; and
aligning and re-shaping the estimate model based

Assignees

• IBM

Inventors

• Blomberg Jeanette L
• Boyette Neil H A
• Chandra Anca A
• Oh Se Chan
• Strong Jr Hovey R

Classifications

• G06Q10/06315 Primary

  Needs-based resource requirements planning or analysis · CPC title