The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
|
Activity Number:
|
286
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 2, 2011 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
| Abstract - #302935 |
|
Title:
|
A Statistical Approach to Forecast Multi-Step Process Durations
|
|
Author(s):
|
Alejandro Veen*+
|
|
Companies:
|
IBM Research
|
|
Address:
|
, , ,
|
|
Keywords:
|
time-to-event data ;
duration forecasting ;
non-parametric ;
survival analysis
|
|
Abstract:
|
The management of multi-step processes is an important problem faced by a large number of businesses. A wide variety of day-to-day operations can in fact be described as multi-step business processes in fields ranging from transportation and manufacturing to various application processes such as applications for licenses, patents, loans, insurance coverage, and even employment positions. One aspect of particular interest is forecasting the duration of the process for a unit of interest (e.g. the application for a government-issued license), given its current step in the process pipeline and additional factors. Instead of explicitly modeling the queuing dynamics, this talk presents a flexible statistical approach based on non-parametric survival analysis. After presenting an example, the strengths and limitations of this approach will be discussed for different types of service science problems.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.