This is a joint call for both the Research Track and the Applied Data Science Track.
In the Research Track, we invite submissions of research papers from all areas in machine learning, knowledge discovery and data mining. Following the tradition of ECML PKDD, we are looking for high-quality papers in terms of novelty, technical quality, potential impact, and clarity of presentation. Papers should demonstrate that they provide a significant contribution to the field (e.g, improve the state-of-the-art or provide a new theoretical insight).
In the Applied Data Science Track, we invite papers that present novel applications of machine learning, data mining and knowledge discovery to solve real world use cases, thereby bridging the gap between practice and current theory. Papers should clearly explain the real world challenge that is being addressed (including any peculiarities of the data, like size of the data set, noise levels, sampling rates, etc), the methodology that is being used, and the conclusions that are drawn for the use case. Please check the FAQ on the website for examples of interesting and less interesting papers for this track.
KEY DATES AND DEADLINES:
All deadlines expire on 23:59 AoE (UTC - 12).
Papers must be written in English and formatted according to the Springer LNCS guidelines. Author instructions, style files and the copyright form can be downloaded here.
The maximum length of papers is 16 pages (including references) in this format. Over-length papers will be rejected without review (papers with smaller than specified page margins and font sizes will be treated as over-length).
Up to 10 MB of additional materials (e.g. proofs, audio, images, video, data, or source code) can be uploaded with your submission. The reviewers and the program committee reserve the right to judge the paper solely on the basis of the 16 pages of the paper; looking at any additional material is at the discretion of the reviewers and is not required.
Electronic submissions will be handled via Microsoft CMT.
Although there are two main tracks in the conference (Research and Applied Data Science), their submission is handled by a single track in CMT. Before submitting, please consider carefully what the appropriate track is (see top of page). The track of choice can then be indicated at the bottom of the submission page. Submissions will be assessed in the track where they were submitted and cannot be transferred across tracks.
To submit a paper, please do the following:
- Create an account and log into the CMT system. (User accounts in CMT are specific for a conference, so you will need to create a new account for this conference.)
- Create a New Paper submission.
- Select the Research Track or the Applied Data Science Track.
- Complete the submission.
Abstracts must be submitted by Friday March 29, 2019 and full submissions must be submitted by Friday April 5, 2019.
Submissions will be evaluated by three reviewers on the basis of novelty, technical quality, potential impact, and clarity. For the applied data science track, one reviewer at least will come from industry. ECML PKDD has a long standing reputation of a truly diverse conference where many topics in Machine Learning and Data Mining are represented. To maintain this, diversity of topics is also taken into account in the selection process. The reviewing process is single-blind (author identities are known to reviewers). Submissions will be assessed in the track where they were submitted and will not be transferred across tracks.
For each accepted paper, at least one author must attend the conference and present the paper. Please make sure to make early travel arrangements and take care of possible immigration requirements (e.g., visa). Information on how to present the paper can be found here.
The conference proceedings will be published by Springer in the Lecture Notes in Computer Science Series (LNCS). The proceedings will be published after the conference and will only include papers that were presented at the conference. Online versions of the papers will be available at the time of the conference.
REPRODUCIBLE RESEARCH PAPERS
Authors are strongly encouraged to adhere to the best practices of Reproducible Research (RR), by making available data and software tools for reproducing the results reported in their papers. Authors may flag their submissions as RR and make software and data accessible to reviewers who will verify the accessibility of software and data. Links to data and code must be inserted in the final version of RR papers. For the sake of persistence and proper authorship attribution, we require the use of standard repository hosting services such as Dataverse, mldata.org, OpenML, figshare, or Zenodo for data sets, and mloss.org, Bitbucket, GitHub, or figshare (where it is possible to assign a DOI) for source code. If data or code gets updated after the paper is published, it is important to enable researchers to access the versions that were used to produce the results reported in the paper. Authors who do not have a preferred repository are advised to consult Springer Nature’s list of repositories and research data policy.
BEST PAPER AWARDS
Two student best paper prizes will be awarded at the conference sponsored by the Data Mining and the Machine Learning journals. In order to be eligible to these awards, the first author of the paper needs to have been a (PhD) student on the day of the submission deadline: April 5, 2019.
DUAL SUBMISSION POLICY
Papers submitted should report original work. We will reject without review any paper that is under review or has already been accepted for publication in a journal or another conference. Authors are not allowed to submit their papers elsewhere during the review period. The dual submission policy applies during the period April 5 - June 7, 2019.
The author list as submitted with the paper is considered final. No changes to this list may be made after paper submission, either during the review period, or in case of acceptance, at the final camera ready stage.
CONFLICTS OF INTEREST
During the submission process, you must enter the email domains of all institutions with which you have an institutional conflict of interest. You have an institutional conflict of interest if you are currently employed or have been employed at this institution in the past three years, or you have extensively collaborated with this institution within the past three years. Authors are also required to identify all Program Committee Members and Area Chairs with whom they have a conflict of interest. Examples of conflicts of interest include: co-authorship in the last five years, colleague in the same institution within the last three years, and advisor/student relation.
What are the awarded papers at the previous ECMLPKDD conferences?
- Here are the awarded Data Mining papers from the last two years:
- Here are the awarded Machine Learning papers from the last two years:
What are papers that are not suited for the applied data science track?
- Papers with an application on one of the UCI dataset without any new problem setting won’t be accepted.
What is the length limit for submitted papers?
- Papers with a maximum length of 16 pages (including references) are accepted for the review process.
- Beneath the paper up to 10 MB of appendix or additional materials (e.g. proofs, audio, images, video, data, or source code) can be uploaded.
Is it allowed to put submitted paper on arxiv?
- Yes, archived papers that have not been submitted or published otherwise (see dual submission policy above) can be submitted to the conference.
If my paper was accepted for ECML PKDD 2019 do I have to give a talk, present a poster or both?
- Both. Each accepted paper has to give a talk and present a poster.