top of page

About me

I am an assistant professor of social data science at the University of Copenhagen at both the Department of Psychology and SODAS. I am interested in combining psychological theory and machine learning methodologies to better understand human behaviour, with applications in social good domains. I am particularly interested in how data-driven methods can help to inform or challenge existing theories in the social sciences. Current work includes looking at how big data can be leveraged to better understand the predictors of educational attainment. Previous work at The Alan Turing Institute used machine learning and AI to help prevent modern slavery and human trafficking.



March 2017 - Present

Analysing academic datasets on student performance using machine learning methods with the goal of understanding bias in the data. Recent research also includes detecting individual differences in digital traces of behaviour in online learning environments.

tree edu.jpeg


2015 - 2019

My PhD used consumer data to investigate how psychological research is best conducted using big data, where the goals are to have interpretable and generalisable models of human behaviour. 

Screenshot 2022-08-02 at 21.58.15.png


October 2019 - 2021

At the Alan Turing Institute I leveraged big data, machine learning and AI to better measure, understand, and ultimately help prevent modern slavery, human trafficking, and other exploitative crimes.

Screenshot 2022-08-02 at 22.05.25.png


June 2019 - August 2019



I was a fellow on the Data Science for Social Good (DSSG) 2019 ran by Imperial College London and in partnership with The University of Chicago, The Alan Turing Institute, and Warwick University. This programme looks at how we can harness the power of data science to enable charities, start-ups, NGOs and governmental departments operating in the social good space to grow. I worked on a project in partnership with IEFP in Portugal, building a recommender system to improve employment outcomes in mainland Portugal.

July 2015 - October 2015


A lot of our daily purchases are driven by various psychological factors. For example, people can buy chocolates either because of habit or because of lapses in self-control when facing a pack of Maltesers at the till. Whilst a wealth of decision-making literature studied psychological mechanisms of impulsive and habitual behaviours in the lab, there is still not enough research translating decision-making theories into real world choices. The Digital Economy opens up a new era in the research of human behaviour, as information about what we buy, where we travel and even what we eat can be recorded “online”, producing evidence that is more accurate than self-reported logs. This project analysed how we categorize and understand different clusters of individual daily decisions and how to interpret the outputs of these analyses.

July 2013 - August 2013



During the 6 week Developmental Psychology internship at the University of Nottingham I actively helped to plan and run the university's Summer Scientist Week (SSW). SSW is a fun filled week for children, which also serves as a pool of participants for the developmental psychology researchers working in and around Nottingham. My role involved event organisation, setting up the data base, testing the children's vocabulary ability using BPVS (including autistic children), calibrating the test scores, as well as analyzing the data.



Deininger, H., Lavelle-Hill, R., Parrisius, C., Pieronczyk, I., Colling, I., Meurers , D., Trautwein, U., Nagengast, B., Kasneci, G. (accepted, AIED 2023). Can You Solve This on the First Try? – Understanding Exercise Field Performance in an Intelligent Tutoring System. 


Lavelle-Hill, R., Lichtenfeld, S., Sakaki, M., Goetz, T., Frenzel, A., Smith., G, Marsh, H., Pekrun, R.  & Murayama, K. (in prep.). Using Machine Learning to Understand how the Predictors of Maths Ability Change over Time.


Lavelle-Hill, R., Smith., G, & Murayama, K. (in prep.). Machine Learning Methods for Large Survey Data in the Social Sciences: Challenges, Solutions, and Future Directions.


Bardach, L., Oczlon, S., Schumacher, A., Lavelle-Hill, R., Lüftenegger, M., & Steffen Zitzmann. (submitted). Teaching and Learning in a Culturally Diverse World: A Meta-Analysis on Cultural Diversity Climate in K-12 Schools.

Lavelle-Hill, R., Harvey, J., Smith, G., Mazumder, A., Ellis, M., Mwantimwa, K., & Goulding, J. (2022). Using mobile money data and call detail records to explore the risks of urban migration in Tanzania. EPJ data science, 11(1), 28.

Lavelle-Hill, R. & Mazumder, A. (2022). AI for Detecting Sexual Exploitation Online in the UK: A Review of Indicators and Ethics. In press (accepted).

Lavelle-Hill, R., Smith, G., Mazumder, A., Landman, T., Goulding, J. (2021) Machine learning methods for “wicked” problems: exploring the complex drivers of modern slavery. Nature Humanities and Social Science Communications 8, 274.

Lavelle-Hill, R., Goulding, J., Smith, G., Clarke, D. D., & Bibby, P. A. (2020). Psychological and demographic predictors of plastic bag consumption in transaction data. Journal of Environmental Psychology, 72, 101473.

Lavelle-Hill, R. E., Skatova, A., Goulding, J., Bibby, P., & Clarke, D. (2020). Buying what people like you buy: Personality Homophily and Well-being in Consumer Behaviour. PREPRINT available at OSF

Tomas, C., Whitt, E., Lavelle-Hill, R., & Severn, K. (2019). Modelling holistic marks with analytic rubrics. In Frontiers in Education (Vol. 4, p. 89). Frontiers.

External Workshops:

Introduction to Machine Learning for Educational Assessment. ZIB academy, DIPF Frankfurt.

September 2022.

Introduction to Machine Learning in Psychology and Education Science. FDZ academy Berlin. March 2022.

Conferences (selected):

EARLI 2023, Thessaloniki, Greece. "Using Machine Learning to Understand how the Predictors of Maths Ability Change over Time."

Data for Policy 2020, London (virtual). "Using Machine Learning Methods to Better Understand the Complexities of Modern Slavery." 

UCL LIDo PhD Programme, London  2020. "Big Data Psychology"

DSSG Data Fest, Imperial College London 2019. "Building a Recommender System to Improve Employment Outcomes in Portugal"

World Conference of Personality, Hanoi 2019. "Bags of money or bags of Impulsiveness? Psychological and Demographic Predictors of Plastic Bag Consumption in Big Data."

European Conference of Personality, Zadar 2018. "Using Machine Learning Techniques to Examine the Relationship between Money, Personality, and Well-being."

GovTechLab Knowledge Transfer Consortium, London, 2018. "Big Data for Social Good"


Winner of CosMo conference "Science Pitch" competition. Tübingen, 2022.

Awarded The University of Nottingham Travel Prize, 2019.

Awarded scholarship and funding by The European Conference of Personality, 2018.

Media Engagements:

Interviewed on NottsTV about research on the predictors of plastic bag purchasing in Jan 2022.

See news coverage from The Independent, The Guardian, and the Daily Mail.

Turing blog post. "Black Friday 2020 survival guide: Will recession or AI save us from impulse buying this year?"

Interviewed on BBC World Service on the psychological and demographic predictors of buying plastic bags in Oct 2020.

Speaker at DSSG Data Fest 2019


University of Tübingen

Post-doctoral Researcher

Machine Learning in Education

2021 - 2023

The Alan Turing Institute

Post-doctoral Researcher

Using AI to Prevent Modern Slavery

2019 - 2021

University of Nottingham

2015 - 2020

University of Nottingham

PhD in "Big Data Psychology" with

N/LAB, Business School and the School of Psychology

1st class (HONS) in BSc Psychology (with international study)
Incl. Cognitive Psychology, Biological Psychology, Neuroscience, Developmental Psychology, Personality and Individual Differences

2011 - 2015

Lund University

2013 - 2014

Universitas 21 Study Abroad Program

Incl. Swedish Language, Cultural Perspectives on Health, Scandinavian History, Evolutionary Psychology, Violence Gender and Culture, Politics in The Middle East, History of the Holocaust


bottom of page