Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Requirements for Crime Prediction Models
The aim of this master thesis is to outline the requirements of a crime prevention IS for the police. More specifically, what are the needs and expectations of the different roles within the police force (e.g. analyst and dispatcher) in respect to crime prediction models in production.
Keywords: crime prediction, applied machine learning, HCI, mockups, police, criminology, semi-structured interview, survey, information systems
The research methodology is expected to comprise:
- Literature review in the relevant HCI/IS, criminology, and applied ML communities
- Semi-structured interview / survey with police forces in the German-speaking part of Switzerland
- Mockup development. Optional: prototype development
The semi-structured interview / survey component of the research is intended to answer questions such as:
- Who are the regular users of the crime prediction IS?
- What are their general needs and expectations i.r.t. the output of a crime prediction model?
- What is the ideal spatio-temporal granularity of the crime prediction model?
- What is the ideal presentation format (e.g. hotspot map, ranked list of high risk streets/areas, decision trees) of the crime prediction model?
- What is the perceived usefulness of the current prediction models?
- How often are crime prediction models consulted and retrained?
As a teaser, current software packages used operationally in USA or Europe include PredPol and HunchLab, watch this video: https://www.youtube.com/watch?v=YxvyeaL7NEM
You should meet following requirements:
- Some knowledge in HCI / IS Research
- Some experience of qualitative methods like semi-structured interviews
- Nice to have: experience in consulting / requirements elicitation. Hands-on experience with mockup tools like Balsamiq.
- Interest in machine learning and its application to the crime domain
- (Close to) native German (interviewing with the police). Proficiency in English (writing up the thesis).
- Strong ability in analyzing, structuring and illustrating results.
The research methodology is expected to comprise: - Literature review in the relevant HCI/IS, criminology, and applied ML communities - Semi-structured interview / survey with police forces in the German-speaking part of Switzerland - Mockup development. Optional: prototype development
The semi-structured interview / survey component of the research is intended to answer questions such as: - Who are the regular users of the crime prediction IS? - What are their general needs and expectations i.r.t. the output of a crime prediction model? - What is the ideal spatio-temporal granularity of the crime prediction model? - What is the ideal presentation format (e.g. hotspot map, ranked list of high risk streets/areas, decision trees) of the crime prediction model? - What is the perceived usefulness of the current prediction models? - How often are crime prediction models consulted and retrained?
As a teaser, current software packages used operationally in USA or Europe include PredPol and HunchLab, watch this video: https://www.youtube.com/watch?v=YxvyeaL7NEM
You should meet following requirements: - Some knowledge in HCI / IS Research - Some experience of qualitative methods like semi-structured interviews - Nice to have: experience in consulting / requirements elicitation. Hands-on experience with mockup tools like Balsamiq. - Interest in machine learning and its application to the crime domain - (Close to) native German (interviewing with the police). Proficiency in English (writing up the thesis). - Strong ability in analyzing, structuring and illustrating results.
The ultimate goal of the thesis is to derive a set of principles for predictive policing IS and specifically for presentation of crime prediction models.
The ultimate goal of the thesis is to derive a set of principles for predictive policing IS and specifically for presentation of crime prediction models.
Please send your application with [Master Thesis – crime prediction IS] in the subject line to: Cristina Kadar, PhD Candidate Chair of Information Management (Professor Elgar Fleisch) D-MTEC, ETH Zurich Homepage: http://www.im.ethz.ch/people/ckadar.html Email: ckadar {at} ethz {dot} ch
Please send your application with [Master Thesis – crime prediction IS] in the subject line to: Cristina Kadar, PhD Candidate Chair of Information Management (Professor Elgar Fleisch) D-MTEC, ETH Zurich Homepage: http://www.im.ethz.ch/people/ckadar.html Email: ckadar {at} ethz {dot} ch