Call for Machine Learning Competition Proposals
FedCSIS at the KnowledgePit Platform
Proposal Submission Deadline: January 31, 2020
We invite academic, industrial, and government organizations to submit the proposals to organize and co-sponsor the Machine Learning Competition at the 15th Conference on Computer Science and Information Systems (FedCSIS 2020).
Machine learning competitions associated with the FedCSIS conference series have a long tradition. Since 2014, they have been organized every year at the KnowledgePit online competition platform, and in total, they have already attracted over 1200 teams from more than 40 countries.
The competition will be broadly announced by the FedCSIS 2020 organizers and the KnowledgePit team.
The top performing competition participants will be invited to present their solutions and publish the associated papers in frame of the Special Competition Session held at FedCSIS 2020.
The official Competition Awards Ceremony will take place during the FedCSIS 2020 banquet. The competition organizers will be invited to attend the banquet and participate in the ceremony.
The opening presentation at the special competition session will be prepared by the KnowledgePit team in cooperation with the competition organizers. The presentation will be jointly affiliated. It is also possible to publish the joint paper describing the competition in the FedCSIS 2020 conference materials.
The competition organizers are expected to sponsor the prizes for the winning teams. In the previous years, we had usually the 1000 USD prize for the winners and 500 USD prize for the second place. The declared prize levels should be described in the submitted competition proposal.
Please note that the FedCSIS 2020 organizers co-sponsor the Machine Learning Competition by providing free registrations for the top-3 participants, and the KnowledgePit team contributes with its time and the ability to use the online competition platform. Therefore, this is a joint effort.
Those who are willing to organize a competition need to remember about the following:
- The tasks should be challenging but achievable within the expected timeline of the competition.
- The data sets should be novel. They cannot be available before the competition begins. The KnowledgePit team will assist in preparation of publicly available versions of the competition data sets.
- The organizers will be requested to cooperate with the KnowledgePit team to comprehensively describe the task and data to the competition participants.
FedCSIS machine learning competitions are usually focused on learning classification / prediction / forecasting models based on the data sets which should be provided by the competition organizers.
The competition should last for several months (see the timeline below). The tasks should be challenging but achievable within the expected timeframe. Participants may use any method they choose.
The data sets cannot be available before the competition begins. The KnowledgePit team will assist you in preparation of publicly available versions of the competition data sets.
The competition organizers will be requested to cooperate with the KnowledgePit team in order to describe the task and the data to the competition participants.
The competition will be hosted at the KnowledgePit platform which includes automatic solution submission and evaluation systems, and provides a leaderboard for the participants.
The competition winners will be selected based on their final rankings, as well as short reports describing their algorithms and results. As already mentioned, the authors of the most successful and interesting solutions will be invited to submit a paper to the special session and attend FedCSIS 2020.
- Step 1 - Submissions of the competition proposals: January 31, 2020
- Step 2 - Proposal evaluation and acceptance decisions: February 7, 2020
- Step 3 - Data release, the start of the competition: February 28, 2020
- Step 4 - Deadline for the competition participants to submit final solutions: May 29, 2020
- Step 5 - Publication of final results and paper submission invitations: June 5, 2020
- Step 6 - Deadline for invited participants to submit their special session papers: June 9, 2020
- Step 7 - Author notification: June 30, 2020
- Step 8 - Final paper submission and registration (free for competition winners): July 15, 2020
We will consider the topics from (but not limited to) the following application domains:
- Health and wellness
- Advanced manufacturing
- Predictive maintenance
- Retail and e-commerce
- Gaming industry
- Smart city and community
Please send the proposals to: firstname.lastname@example.org
Remember about the submission deadline: January 31, 2020.
The proposals will be evaluated based on the significance and novelty of the considered problem, clarity of its specification, and availability of the related data.
The proposals should answer to the following questions:
- Who are the Competition Organizers? Provide names, affiliations, contact information, brief bios.
- Which sector / application domain is considered in the proposed machine learning competition?
- What is the considered task? Which evaluation metrics are proposed to evaluate the solutions?
- (If you are not sure about the appropriate choice of the evaluation metrics, such as accuracy, F1-score etc., the KnowledgePit team is ready to assist you.)
- What kind of data set will be provided? Please describe its essential characteristics.
- (If there are privacy concerns regarding the data, please explain in detail. The KnowledgePit team may provide additional services regarding the data anonymization. Please contact us for more information.)
- What prizes will be offered to the winners?
- (As already mentioned, it is expected that the competition organizers will sponsor the prizes at the level of at least 1000 USD for the winners and 500 USD for the second place.)
It is the standard that Intellectual Property associated with the solutions submitted by the competition winners will be owned by the competition organizers who sponsored the prizes. For more details, please contact us at: email@example.com