Back to search results

Developing Crime Predictive Models and Evaluating the Utility of Prediction Outputs Amongst Crime Prevention Practitioners

University of Essex - Department of Psychology

Qualification Type: PhD
Location: Colchester
Funding for: UK Students, EU Students, International Students
Funding amount: £15,009 plus a full Home/EU fee waiver or equivalent fee discount for overseas students
Hours: Full Time
Placed On: 13th February 2020
Closes: 31st March 2020

Funding: A full Home/EU fee waiver or equivalent fee discount for overseas students  (£5,103 in 2020-21) (further fee details - international students will need to pay the balance of their fees) plus a doctoral stipend equivalent to the RCUK Minimum Doctoral Stipend (£15,009 in 2019-20, stipend for 2020-21 tbc).

Application deadline: Tuesday 31 March 2020

Start date: October 2020

Duration: 3 years (full time)

Location: Colchester Campus

Based inDepartment of Psychology (in collaboration with Department of Mathematical Sciences)


The aim of this cross-disciplinary PhD is to better inform and improve the decision-making capacity of police officers so that we can prevent crime and speed up police interventions.

We will develop machine learning models predicting in which environmental settings crimes are more likely to take place in order to improve the effectiveness of police interventions and the well-being of the population.

The project

The project will span two stages, both involving psychology and data science in a real and in-depth collaboration.

First, the project will involve developing a series of predictive models based on a wide range of crime data held by police as well as environmental factors (e.g. population density, deprivation index, amenities etc.). The predictive models will be based on past data provided by the Essex Police and will help to identify hotspots where crimes are more likely to happen so that resourcing can be allocated more effectively to reduce crime rate and target police interventions.

A series of psychological experiments will then examine the extent to which different predictive models are accurate and can improve staff resource allocation in game-like simulations with human participants.

In a second phase, we will focus on maximising decision quality and measuring and curbing particular cognitive and social biases expected to occur when practitioners rely on algorithms probabilities.

We will focus on the cognitive trend bias (e.g., increasing probabilities are seen as even more certain), the cognitive over-reliance on extreme probabilities (e.g., one can fail to consider a 20% chance of no event when there is an 80% probability of a crime taking place) using the same resource allocation game as before.

We will also consider the social consequence of using the algorithms for specific communities using a stop and search decision task.


Dr Marie Juanchich – Lead Supervisor

Dr Hongsheng Dai – Co-Supervisor

How to apply  

You can apply for this postgraduate research opportunity online.

Please include your CV, a cover letter, and transcripts of UG and Masters degrees in your application.

If you are an international applicant who will require a Tier 4 visa please also include a personal statement in your application.

The University has moved to requiring only one reference for PhD applications and these can be received after a conditional offer has been made so the absence of these will not hold up the recruitment process.

Find out more about this studentship and information on how to apply on our website.

We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

Subject Area(s):


PhD tools
More PhDs from University of Essex

Show all PhDs for this organisation …

More PhDs like this
Join in and follow us

Browser Upgrade Recommended has been optimised for the latest browsers.

For the best user experience, we recommend viewing on one of the following:

Google Chrome Firefox Microsoft Edge