Smart Analytics for Forecasting Parts Returns for Reutilization

• US 20140244356A1
• Filed: 09/11/2013
• Published: 08/28/2014
• Est. Priority Date: 02/27/2013
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Boniello, Jeffrey M., Hay, Michael B., La Fera, Vincent E., Lin, Pitipong Jun Sen, O'Connor, Kevin P., Palya, Borbala, Parks, John G., Thankamony, Jacob
• Application Number:
  US14/023,896
• Publication Number:
  US 20140244356A1
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

An approach is provided in which the approach maps first parts included in a first system to second parts included in a second system. The approach then utilizes functioning first parts returns data, which indicates an amount of parts included in the first system that have been returned and are functioning, to forecast an amount of functioning parts corresponding to the second system to be returned. As such, the approach generates a functioning second parts returns forecast based upon the amount of functioning second parts that are forecast to be returned.

Claims

1. A method comprising:

mapping, by one or more processors, one or more first parts included in a first system to one or more second parts included in a second system;

retrieving, by one or more of the processors, functioning first parts returns data that indicates an amount of one or more of the first parts that have been returned and are functioning;

forecasting, by one or more of the processors, an amount of one or more of the second parts to be returned and functioning based upon the functioning first parts returns data and the mapping of one or more of the first parts to one or more of the second parts; and

generating, by one or more of the processors, a functioning second parts returns forecast based upon the forecasted amount of one or more of the second parts.

2. The method of claim 1 further comprising:

computing a first parts returns lag time based upon a first system production start time and a first parts returns start time;

determining whether one or more of the second parts have been returned; and

in response to determining that one or more of the second parts have not been returned, computing a second parts returns start time based upon the first parts returns lag time and a second system production start time corresponding to the second system.

3. The method of claim 2 further comprising:

in response to determining that one or more of the second parts have been returned, computing the second parts returns start time based upon an actual time that one or more of the second parts have been returned.

4. The method of claim 3 further comprising:

generating a first parts returns curve based upon the functioning first parts returns data, wherein the first parts returns curve graphs the amount of one or more of the first parts that have been returned over time; and

generating a second parts returns forecast curve based upon the first parts returns curve, the second parts returns start time, and the forecasted amount of one or more of the second parts, wherein the functioning second parts returns forecast is based upon the second parts returns forecast curve.

5. The method of claim 4 wherein, prior to generating the second parts returns forecast curve, the method further comprises:

analyzing the first parts returns curve, wherein the analyzing is selected from the group consisting of a uniform analysis, a linear regression analysis, and an autoregressive integrated moving average analysis; and

wherein the generation of the second parts returns forecast curve is based upon the analyzing of the first parts returns curve.

6. The method of claim 1 further comprising:

retrieving a second system production forecast that indicates a production rate of the second system type; and

generating a second system new parts order plan based upon the second system production forecast and the functioning second parts returns forecast.

7. The method of claim 1 wherein the mapping further comprises:

selecting one of the second parts;

identifying a part group that corresponds to the selected second part;

identifying a part category, within the identified part group, that corresponds to the selected second part;

identifying a first part that is included in the identified part category within the identified part group; and

mapping the selected second part to the identified first part.

8. The method of claim 1 wherein, prior to the mapping, the method further comprises:

retrieving first system type quantity data and first system type timing data;

retrieving second system type forecast quantity data and second system type forecast timing data;

comparing the first system type quantity data to the second system type forecast quantity data;

analyzing the first system type timing data against the second system type forecast timing data; and

determining that the first system type correlates to the second system type in response to the comparing and the analyzing.

9. The method of claim 8 further comprising:

computing a system forecast ratio based upon the first system type quantity data and the second system type forecast quantity data; and

utilizing the system forecast ratio during the forecasting of the amount of functioning second parts.

10. A method comprising:

mapping, by one or more processors, one or more first parts included in a first system to one or more second parts included in a second system;

retrieving, by one or more of the processors, functioning first parts returns data that indicates an amount of one or more of the first parts that have been returned and are functioning;

forecasting, by one or more of the processors, an amount of one or more of the second parts to be returned and functioning based upon the functioning first parts returns data and the mapping of one or more of the first parts to one or more of the second parts;

computing, by one or more of the processors, a first parts returns lag time based upon a first system production start time and a first parts returns start time;

determining, by one or more of the processors, whether one or more of the second parts have been returned;

in response to determining that one or more of the second parts have not been returned, computing a second parts returns start time based upon the first parts returns lag time and a second system production start time corresponding to the second system;

in response to determining that one or more of the second parts have been returned, computing the second parts returns start time based upon an actual time that one or more of the second parts have been returned;

generating, by one or more of the processors, a first parts returns curve based upon the functioning first parts returns data, wherein the first parts returns curve graphs the amount of one or more of the first parts that have been returned over time;

generating, by one or more of the processors, a second parts returns forecast curve based upon the first parts returns curve, the second parts returns start time, and the forecasted amount of one or more of the second parts; and

generating, by one or more of the processors, a functioning second parts returns forecast based upon the generated second parts returns forecast curve.