[agents] PhD position *Probabilistic Decision Support for Forensic Investigations* at Utrecht University

[Floris Bex]

We are looking for an enthusiastic PhD candidate for our PROBAS project
(Probabilistic decision-making Based on Arguments and Scenarios). In this
project, fundamental research on language, logic and algorithms is combined
with research into knowledge elicitation and decision-support in the
context of large forensic investigations.

**Job description**
The probabilistic Bayesian network formalism can provide the basis for
decision support in complex investigative domains where uncertainty plays a
role (e.g. forensics, risk assessment). Yet, Bayesian networks are only
sparsely used in practice because domain experts use more informal
concepts, such as scenarios and arguments, which convey verbally expressed
uncertainty (“strong arguments for the suspect’s guilt”, “plausible
scenarios in which the suspect is innocent”). We therefore need to engineer
tools for Bayesian network construction into the heart of the
decision-making process. These tools should be based on familiar, more
linguistically-oriented concepts such as arguments and scenarios, and
complemented by algorithms intended to speed up and facilitate the process
of building Bayesian networks.

The aim of this interdisciplinary project is to determine how arguments and
scenarios are used in actual decision-making, how they can be used to
construct and compare Bayesian networks, and how subsequently mathematical
and computational techniques can be used to refine and choose between
alternative networks.

The PhD candidate will perform case studies at the Dutch police on
investigation and operational risk assessment, design knowledge-elicitation
techniques based on scenarios and arguments and study mathematical and
computational techniques for comparing Bayesian networks. The knowledge
elicitation techniques and algorithms developed will be implemented in
software services that connect to existing and new interfaces at the Dutch
police.

The candidate will be part of the department of Information and Computing
Sciences' Artificial Intelligence division, working with the Intelligent
Systems group (Floris Bex, Henry Prakken) and the Decision Support Systems
group (Silja Renooij, Linda van der Gaag), in close partnership with the
Dutch National Police.

**Qualifications**
A prospective candidate has a master's degree in Artificial Intelligence,
Computer Science, Information Science, Mathematics or a related field. The
candidate should have solid mathematical knowledge and programming skills
and an interest in formal research in argumentation, scenario-based
reasoning and Bayesian networks, and their application in forensic/police
contexts.

The ideal candidate should have excellent academic qualifications as well
as good communication and collaboration skills, and candidates are expected
to be in the upper segment of their class with respect to academic
credentials and must show interest in both research and
teaching/supervision activities.

**Conditions of Employment**
The candidate is offered a full-time position for four years.

Salary starts at € 2,191 and increases to € 2,801 gross per month in the
fourth year of the appointment. The salary is supplemented with a holiday
bonus of 8% and an end-of-year bonus of 8,3% per year. In addition we
offer: a pension scheme, a partially paid parental leave, flexible
employment conditions. Conditions are based on the Collective Labour
Agreement Dutch Universities. The research group will provide the candidate
with necessary support on all aspects of the project.

**Employer**
The city of Utrecht is one of the oldest cities in the Netherlands, with a
charming old centre and an internationally oriented culture that is
strongly influenced by its century-old university. Utrecht city has been
consistently ranked as one of the most livable cities in the Netherlands.

Utrecht University's faculty of Science consists of six departments:
Biology, Pharmaceutical Sciences, Information and Computing Sciences,
Physics and Astronomy, Chemistry and Mathematics. The faculty is home to
4800 students and nearly 1500 staff and is internationally renowned for the
quality of its research. The faculty's academic programmes reflect
developments in today's society.

The department of Information and Computing Sciences has a strong national
and international reputation in computer science and AI. Research activity
within the department is housed in the Institute of Information and
Computing Sciences and comprises four divisions: Artificial Intelligence,
Interaction technology, Software systems and Virtual worlds. The PhD
candidate will become part of the Artificial Intelligence division.

**Additional Information**
Additional information about the vacancy can be obtained from: dr Floris
Bex, F.J.Bex at uu.nl, or dr Silja Renooij, S.Renooij at uu.nl. A more detailed
project description can be provided upon request.

**Applying**
Application is through the online application system of Utrecht
University (link
to job posting
<https://ssl1.peoplexs.com/Peoplexs22/CandidatesPortalNoLogin/Vacancy.cfm?PortalID=4124&VacatureID=850312&Vacancy=PhD%20position%20%22Probabilistic%20Decision%20Support%20for%20Forensic%20Investigations%22%20%281%2C0%20FTE%29#top>,
with application button). Please attach a letter of motivation, curriculum
vitae and (email) addresses of two referees. It is possible to apply for
this position if you are close to obtaining your Master's degree. In that
case include a letter of your supervisor with an estimate of your progress.

The application deadline is *October 1, 2016*