Session

Information Systems and Security

Description

Machine Learning and Robust Optimization techniques can significantly improve logistics operations and improve stock quantity and maintenance intervals. Machine Learning will be used to forecast item demands for each of the vending machines, taking into account past demands and calendar effects. By performing such predictions which are forwarded to a Robust Optimization model, and whose outputs will be the cash transport that each vending machine should require. These transports guarantee that demand is fulfilled up to the desired confidence level, preventing downtime of vending machines due to unplanned maintenance and out-of-stock situations, while also satisfying additional constraints arising in this particular domain. As a result of such operations, we expect productivity improvements of vending machines from 20-40%.

Keywords:

Machine Learning, vending machines, IoT, optimization techniques

Session Chair

Agon Mehmeti

Session Co-Chair

Blerton Abazi

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-437-96-7

First Page

12

Last Page

21

Location

Lipjan, Kosovo

Start Date

31-10-2020 9:00 AM

End Date

31-10-2020 10:30 AM

DOI

10.33107/ubt-ic.2020.211

Share

COinS
 
Oct 31st, 9:00 AM Oct 31st, 10:30 AM

Making vending machines smarter with the use of Machine Learning and Artificial Intelligence: Set-up and Architecture

Lipjan, Kosovo

Machine Learning and Robust Optimization techniques can significantly improve logistics operations and improve stock quantity and maintenance intervals. Machine Learning will be used to forecast item demands for each of the vending machines, taking into account past demands and calendar effects. By performing such predictions which are forwarded to a Robust Optimization model, and whose outputs will be the cash transport that each vending machine should require. These transports guarantee that demand is fulfilled up to the desired confidence level, preventing downtime of vending machines due to unplanned maintenance and out-of-stock situations, while also satisfying additional constraints arising in this particular domain. As a result of such operations, we expect productivity improvements of vending machines from 20-40%.