PhD Candidate, Interpretable causal machine learning for intervention development from wearable sensors data

at Leiden University
Published March 22, 2023
Location Leiden, Netherlands
Category Machine Learning  
Job Type Scholarship  



The Faculty of Science and the Leiden Institute of Advanced Computer Science (LIACS) are looking for a :

PhD Candidate, Interpretable causal machine learning for intervention development from wearable sensors data
Vacancy number: 23-204

Key responsibilities

We are looking for an excellent candidate with a master’s degree in MSc in Artificial Intelligence, Computer Science, Mathematics, Statistics, or a closely related field to join a project focused on health intervention development using wearable sensing technologies.
We would like to understand how 24/7 observational activity data collected by wearable sensors (e.g., smart watches) and causal machine learning techniques (casual discovery and causal inference) can be used to identify and recommend effective changes in daily activities (i.e., possible behavioral interventions) that are expected to result in concrete health improvements. Available machine learning techniques are not able to fully identify causal mechanisms from observational data. Within this project our goal is to develop algorithms for finding causal relations which subsequently can be the starting point for effective interventions and inferring the impact of behavioural changes.
This project is defined within the LABDA (Learning Network for Advanced Behavioural Data Analysis) European project:

LABDA is an EU-funded Marie Sklodowska Curie Action (MSCA) Doctoral Network, that brings together leading researchers in advanced movement behaviour data analysis at the intersection of data science, method development, epidemiology, public health, and wearable technology to train a new generation of creative and innovative public health researchers via training-through-research. The main aims of LABDA are to establish novel methods for advanced 24/7 movement behaviour data analysis of sensor-based data, examine the added value of advanced behavioural data analysis and multi-modal data for predicting health risk and facilitate the use and interpretability of the advanced methods for application in science, policy and society. Via training-through-research projects, 13 doctoral fellows will contribute to reaching these aims. Together, they will develop a joint taxonomy to enable interoperability and data harmonisation. Results will be combined in an open-source LABDA toolbox of advanced analysis methods, including a decision tree to guide researchers and other users to the optimal method for their (research) question. The open-source toolbox of advanced analysis methods will lead to optimized, tailored public health recommendations, and improved personal wearable feedback concerning 24/7 movement behaviour. For more information, see the project’s website:

As a doctoral fellow/PhD candidate within this project your specific responsibilities will be to
●    Perform research in causal discovery with the goal of developing methods to identify possible interventions from observational 24/7 movement behaviour time-series data;
●    Perform research in counterfactual prediction and developing a framework for counterfactual prediction from 24/7 movement behaviour time-series data;
●    Enhance the robustness of counterfactual prediction methods 24/7 movement time-series data;
●    Report on findings by publishing scientific articles, resulting in a dissertation;
●    Present findings at (inter)national meetings/conferences;
●    Collaborate and exchange knowledge and skills with the other LABDA fellows;
●    Contribute to the LABDA toolbox of advanced analysis methods for sensor-based behavioural data;
●    Contribute to educational activities of the department and within the consortium.


Selection Criteria 
All applicants need to fulfill the MSCA
basic requirements (applications that do not meet these requirements will not be reviewed):

●    Doctoral candidate: all researchers recruited in a Doctoral Network must be doctoral candidates, i.e., not already in possession of a doctoral degree at the date of the recruitment;
●    Mobility Rule: doctoral candidates must not have resided or carried out their main activity (work, studies, etc.) in the Netherlands for more than 12 months in the 3 years immediately before the recruitment date. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account.

Additionally, our selection criteria include:

●    Holding (or close to acquiring) an MSc degree in Artificial Intelligence, Computer Science, Mathematics, Statistics or a closely related field;
●    Strong skills in machine learning;
●    Familiarity with machine learning algorithms for time-series/wearable sensors data;
●    Familiarity with causal inferences and causal discovery methods;
●    Strong programming skills in Python or other programming languages;
●    Strong command of the English language;
●    Willingness and proven ability to work independently, but also in the context of international collaborations.


Terms and conditions 
We offer a full-time appointment of initially one year. After a positive evaluation of the progress of the research, teaching evaluations, personal capabilities and compatibility, the appointment will be extended for another three years. The salary will be in pay scale P in accordance with the Collective Labour Agreement for Dutch Universities) and in accordance with the allowance model of the MSCA Doctoral Networks (see the table on page 81 for details), subject to national taxation and social contributions.

Leiden University offers an attractive benefits package with additional holiday (8%) and end-of-year bonuses (8.3%), training and career development and sabbatical leave. Our individual choices model gives you some freedom to assemble your own set of terms and conditions. Candidates from outside the Netherlands may be eligible for a substantial tax break.
All our PhD students are embedded in the Leiden University Graduate School of Science Our graduate school offers several PhD training courses at three levels: professional courses, skills training and personal effectiveness. In addition, advanced courses to deepen scientific knowledge are offered by the research school.


Research at our faculty
The Faculty of Science is a world-class faculty where staff and students work together in a dynamic international environment. It is a faculty where personal and academic development are top priorities. Our people are committed to expand fundamental knowledge by curiosity and to look beyond the borders of their own discipline; their aim is to benefit science, and to make a contribution to addressing the major societal challenges of the future.
The research carried out at the Faculty of Science is very diverse, ranging from mathematics, information science, astronomy, physics, chemistry and bio-pharmaceutical sciences to biology and environmental sciences. The research activities are organized in eight institutes. These institutes offer eight bachelor’s and twelve master’s programmes. The faculty has grown strongly in recent years and now has more than 2.300 staff and almost 5,000 students. We are located at the heart of Leiden’s Bio Science Park, one of Europe’s biggest science parks, where university and business life come together.
For more information, see and


D&I statement
Diversity and inclusion are core values of Leiden University. Leiden University is committed to becoming an inclusive community which enables all students and staff to feel valued and respected and to develop their full potential. Diversity in experiences and perspectives enriches our teaching and strengthens our research. High quality teaching and research is inclusive.

Inquiries about the research area can be made to Dr. Mitra Baratchi ( ).
If you have any questions about the procedure, please contact Anne-Marie Alleblas ( )