EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3285. Assignment optimization with decision-dependent completion times for trademark application evaluation
Invited abstract in session TC-6: Advancements of OR-analytics in statistics, machine learning and data science 14, stream Advancements of OR-analytics in statistics, machine learning and data science.
Tuesday, 12:30-14:00Room: 1013 (building: 202)
Authors (first author is the speaker)
| 1. | Shabnam Kilic
|
| 2. | Ozlem Karsu
|
| Industrial Engineering, Bilkent University | |
| 3. | Taghi Khaniyev
|
| Industrial Engineering, Bilkent Universitesi |
Abstract
In this work, we consider an assignment problem with decision-dependent completion times which is motivated by a real-life application in trademark evaluations. We formulate the problem of assigning evaluations to agents as a Mixed Integer Programming (MIP) model to help decision-makers better assign workers to evaluation tasks, considering their expertise and current workload. The aim is to minimize the backlog level of the office, which is quantified by the total number of tardy jobs. We provide two alternative formulations and explore their computational performance on a large number of test instances. We integrate both linear and neural network prediction models by using machine learning algorithms and evaluate the improvements in the total number of tardy jobs.
Keywords
- Machine Learning
- Analytics and Data Science
- Expert Systems and Neural Networks
Status: accepted
Back to the list of papers