INCOM 2024Description
This is a logistics and supply-chain data competition organised within INCOM 2024 (https://www.incom2024.org/), open for all participants registered for the conference. Participants can register as a team or as individuals through this link: https://forms.gle/67ixpD3Fy8uEH7H57. The exact problem and dataset will be made available to the participants a day before the conference commences.
The competition comprises two segments, one for a logistics problem and the other for a supply chain problem. Participants can choose to participate in both or either one of the segments. There will be a winner in each segment. These are further detailed below:
-
Segment 1: Logistics competition
- Problem: This segment includes solving a collaborative vehicle routing problem, called a multi-depot capacitated vehicle routing problem (MDCVRP). Logistics industries often face low truck space utilisation. Around one third of trucks traveling on the road are empty, making collaboration between carriers a promising avenue for tackling this low utilisation. In this segment, participants will be presented with a goal to minimise the total travel distance of trucks, with each truck leaving their own depot to fulfil a collection of customer demands and then return to the original depot after completing delivery tasks. The capacity of trucks is capped uniformly.
- Testing: The MDCVRP instances will be generated in a 1000×1000 Euclidean space. A collection of example instances will be provided mid- August, 2024 for the participants to develop their model and codes. Participants can then test their models using the example instances. Real instances for the competition will be revealed a day before the conference.
- Evaluation Metric: An ideal routing algorithm shall minimise the total distance of routes under a reasonable time period. The models will be firstly evaluated based on the total length of routes and secondly based on computation efficiency.
-
Segment 2: Supply Chain Competition
- Problem: This is a multi-label delivery delay prediction problem, which is a challenge often encountered by supply chain practitioners from various industries in their daily operations. Here, the participants assume the role of procurement professionals in an industry to develop models to predict the arrival status of delivery, either arrival early, on time or delay.
- Testing: A tabular dataset that consists of a set of variables related to delivery will be provided to the participants to develop their delay prediction models. Example dataset will be provided around mid-August, 2024 to the participants for their model development and testing. Real dataset for the competition will be revealed a day before the conference.
-
Evaluation Metric: An ideal delay prediction algorithm shall be able to accurately predict delivery arrival status.
In addition to the winners in each segment described above, a special prize will also be reserved for the most innovative algorithmic approach, and certificates of participation will be awarded to all registered participants.
Winners will be announced during the conference closing session.
Competition data and details will be uploaded to the INCOM 2024 Website (https://www.incom2024.org/data-challenge/) and posted in the LinkedIn (https://www.linkedin.com/company/supply-chain-ai-lab/) of the Supply Chain AI Lab, University of Cambridge in due course.
Organisers:
Prof. Alexandra Brintrup, University of Cambridge
Dr. Liming Xu, University of Cambridge
Dr. George Baryannis, University of Huddersfield
Prof. Dmitry Ivanov, Berlin School of Economics and Law
Please contact Dr Liming Xu (email: lx249@cam.ac.uk) for any questions.