The Data and AI cluster at Eindhoven University of Technology (TU/e) is searching for candidates for one fully-funded 5-year PhD-TA position. Of the time in the position, 75% will be spent on fundamental scientific research: the primary goal is to enrich the portfolio of available data mining techniques with new innovative methods. The remaining 25% of the time in the position will be spent contributing to the teaching duties of the Data and AI cluster. Hence, this position is an ideal springboard for an academic career: during your PhD trajectory, in which you will contribute fundamental advances to data mining research, you will also build up a portfolio of academic teaching experience. Upon successful completion of this position, your CV will be very attractive for universities with open tenure-track positions.
The scientific framework in which the position is grounded is Exceptional Model Mining (EMM), a data mining framework that strives to find subgroups within a dataset that are interesting. Subgroups are only deemed interesting if they satisfy two conditions. On the one hand, they must be interpretable: we must be able to succinctly describe the definition of a subgroup, so that the knowledge that they represent becomes actionable. On the other hand, they must be exceptional: they must display some kind of behavior that sets them apart from overall behavior. The scientific challenges revolve around how to efficiently search for subgroups, and how to express exceptional behavior such that the subgroups we find are meaningful.
Making an efficient traversal of the combinatorially-large subgroup search space is already challenging in traditional, cross-sectional data. In this PhD position, the main research challenge is to create efficient algorithms to search for exceptional subgroups in data that varies over time. The problem space encompasses both heuristic algorithms, such as Monte-Carlo Tree Search and Pattern Sampling, and exhaustive algorithms, where we will investigate Optimistic Estimates, GP-Growth, and Significant Pattern Mining. We may also look into whether the anytime algorithm with guarantees for Subgroup Discovery, called 'Refine&Mine', can be expanded to EMM settings. Completely fresh algorithmic ideas to tackle EMM are also most welcome. Please consult the PDF-document
for further details about the project description encompassing this PhD position.
TU/e is a dynamic, research-intensive university in the heart of Europe. TU/e is consistently ranked within the top-100 positions in several world rankings for its research and quality of education. The Data and AI cluster consists of 18 professors, 1 lecturer, 3 postdoctoral researchers, 41 PhD students, and 7 research engineers. The research results of the cluster appear in top-tier conferences and journals including but not limited to SDM, KDD, ECML PKDD, ICDM, AAAI, DAMI, MACH, and KAIS. The cluster has close collaboration with several leading companies, organizations, and hospitals.
The successful candidate will be based in the Data Mining group of the DAI cluster, where opportunities are available to collaborate with other PhDs and to co-supervise MSc students on topics relevant to your research. Your research will be concluded with a PhD thesis. You will be supervised by dr. Wouter Duivesteijn and prof. dr. Mykola Pechenizkiy.