Currently we have the following offer for a post-doc job:

Position Announcement: Post-doc – Full-time Employment
Institution Name: Faculty of Computing and Telecommunications, Poznan University of Technology, Poznan, Poland

Requirements:

  1. A Ph.D. degree obtained not earlier than January 1st, 2018, in one of the following scientific disciplines: computer science, econometrics, management, or mathematics.
  2. The Ph.D. degree should have been obtained from an institution other than the Poznan University of Technology, or the candidate has completed at least a 10-month continuous and documented postdoctoral fellowship at an institution other than the Poznan University of Technology and in a country other than the country of obtaining the Ph.D. degree.
  3. Basic knowledge of operational research and artificial intelligence, particularly in intelligent decision support systems.
  4. Familiarity with basic programming languages (Python, Java).
  5. Documented research experience with publications in the required knowledge area.
  6. At least a good command of English in both speech and writing.
  7. Attributes such as availability, willingness for self-development, strong motivation for research work, creativity in problem-solving, independence, reliability, and teamwork skills.

We offer:

  • The opportunity to work on a prestigious, interdisciplinary, and pioneering MAESTRO project led by an experienced scientist, Prof. Roman Słowiński (https://fcds.cs.put.poznan.pl/IDSS/rslowinski/cv_en.htm).
  • Work within an international team, in collaboration with the University of Catania, including visits to this institution.
  • Participation in scientific conferences both domestically and abroad to present the project results.

Job description:

The position involves participation in an interdisciplinary and pioneering project, “Intelligent Decision Support Based on Explanatory Analytics of Preference Data” led by Professor Roman Słowiński. The objective is to develop innovative algorithms and conduct computational experiments resulting in publications in leading scientific journals. Key focus areas include:

  1. Consensus Reaching Process in Group Decision-Making with explanatory models of decision-makers’ preferences.
  2. Enhanced Algorithms for Decision Rule Induction and Classifier Ensemble Construction composed of diverse sets of decision rules.

Ad. 1. Based on the observation that many previous studies on group decision-making did not pay enough attention to individual participation and satisfaction of DMs in the decision-making process, we proposed in [Y. Zhao, Z. Gong, G. Wei, R. Słowiński, Consensus modeling with interactive utility and partial preorder of decision-makers, involving fairness and tolerant behavior. Information Sciences, 638 (2023) 118933, https://doi.org/10.1016/ j.ins.2023.118933] a new kind of consensus models for group utility optimization. An interesting follow-up of this study would consist in the application of robust ordinal regression for determining a representative collective utility function based on preference information reflecting the value systems of individual DMs.
Another way of determining a representative collective preference model would be possible if individual preferences of DMs would be represented by “if…, then…” decision rules. It would be consistent with explainable preference analytics. Then, the preference information of all DMs provided in terms of pairwise comparisons or classifications of some reference alternatives would be used by Dominance-based Rough Set Approach to induce a collective rule preference model guiding interactively the consensus-reaching process.

Ad. 2. All tasks of the project are based on representation of preferences in terms of “if…, then…” decision rules. The methodology of rule induction from ordinal data employs Dominance-based Rough Set Approach. The methodology has been described in [M. Szeląg, R. Słowiński, Explaining and predicting customer churn by monotonic rules induced from ordinal data. European Journal of Operational Research, 317 (2024) no.2, 414-424. https://doi.org/10.1016/ j.ejor.2023.09.028]. Another topic of decision rule induction that is worth investigation is construction of ensemble classifiers composed of diversified basic classifiers. The basic classifiers would be sets of “if…, then…” decision rules obtained by algorithms developed within this task. The method for finding diversified basic classifiers would rely on preliminary results obtained in [J. Błaszczyński, B. Prusak, R. Słowiński: Multi-objective search for comprehensible rule ensembles. In: V. Flores et al. (eds.): IJCRS 2016, LNAI 920, Springer, Berlin, 2016, pp. 503-513, https://doi.org/10.1007/978-3-319-47160-0_46].

Type of NCN competition: MAESTRO project
Deadline for submissions: December 15, 2024
Submission method: e-mail

Employment conditions:
Duration: 12 months, with the possibility of extension Employment form2: employment contract
Funding amount: salary of PLN 8,660 per month
Start date: Q1 2025

Candidates are requested to submit an application consisting of:

  1. CV with a cover letter.
  2. Ph.D. diploma and a description of the defended doctoral dissertation.
  3. List of publications and copies of up to 3 of the best ones.
  4. Name, surname, position, and email address of a person who can provide a reference.
  5. Statement or certificate of English proficiency.
  6. Statement of programming language proficiency.
  7. Statement of consent for the processing of personal data for recruitment purposes with the following content: „I consent to the processing of my personal data contained in the application documents by the Poznań University of Technology, located in Poznań, for the purpose of conducting the current recruitment process.„

Interested candidates should send the required documents to roman.slowinski@put.poznan.pl by December 15, 2024.
Competition outcome date: December 30, 2024.