Dr.ir. S. (Sander) van Cranenburgh
I am Associate Professor of Choice modelling. My research aim is to develop new models for enhancing our understanding of human choice behaviour. Understanding choice behaviour and being able to predict it is essential to the efficient functioning of society. For instance, it enables making appropriate provisions to accommodate travel demand when a new railway line is constructed, or when a new service is being introduced.
In my recent work I focus on new models and methods that bridge the gap between theory-driven discrete choice models and data-driven machine learning models. Until recently, the discrete choice modelling field was almost exclusively based on theory-driven models. In my work I try to push the frontier of my field by bringing these major modelling paradigms together. Doing so creates new tools to investigate choice behaviour that hold the potential to get the best of both: the flexibility and versatility of data-driven models and the rigorous behavioural inference provided by theory-driven models.
I’m director of TUD’s CityAI Lab. At this lab we want to bring together AI and behavioural theory to capture the fabric of cities, in terms of things like attractiveness, safety, quality of life and accessibility, and to understand their impacts on behaviour and experiences.
In my Post-doc years (2013-2014) I have made a series of contributions to Random Regret Minimisation (RRM) based discrete choice models. RRM models are a behaviourally inspired counterpart of the classical Random Utility Maximisation model. I have developed: a new family of RRM models, new data collection methodology, and the world’s first RRM-based national transport model. See my personal website www.advancedRRMmodels.com for the latest developments in Random Regret Minimization (RRM) modelling, experimental design software for RRM models (Ngene & MATLAB), and estimation codes for RRM models for Biogeme (Bison, Python & Pandas), R (Apollo), MATLAB, and LatentGold Choice.
- Travel behaviour research: the state-of-the-art
2019/2020
Master Complex Systems Engineering & Management
ECTS: 5 - Kwantitatieve modellen voor transport
2019/2020
Bachelor Technische Bestuurskunde
ECTS: 5
- Van Cranenburgh, S., Kouwenhoven M. (2019) Using Artificial Neural Networks for Recovering the Value-of-Travel-Time Distribution. In: Rojas I., Joya G., Catala A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science, vol 11506. Springer, Cham. DOI: 10.1007/978-3-030-20521-8_8.
- Van Cranenburgh, S. & Alwosheel, A. (2019). An artificial neural network based approach to investigate travellers’ decision rules. Transportation Research Part C: Emerging Technologies, 98, 152-166. DOI: 10.1016/j.trc.2018.11.014
- Alwosheel, A., Van Cranenburgh, S. & Chorus, C.G. (2019). ‘Computer says no’ is not enough: Using prototypical examples to diagnose artificial neural networks for discrete choice analysis. Journal of Choice Modelling, DOI: 10.1016/j.jocm.2019.100186
- Van Cranenburgh, S., Rose, J. M. & Chorus, C. G. (2018). On the robustness of efficient experimental designs towards the underlying decision rule. Transportation Research Part A: Policy and Practice, 109, 50-64. DOI: 10.1016/j.tra.2018.01.001.
- Van Cranenburgh, S. & Collins, A. T. (2019). New software tools for creating stated choice experimental designs efficient for regret minimisation and utility maximisation decision rules. Journal of Choice Modelling, 31, 104-123. DOI: 10.1016/j.jocm.2019.04.002.
- Van Cranenburgh, S., Guevara, C. A. & Chorus, C. G. (2015). New insights on random regret minimization models. Transportation Research Part A: Policy and Practice, 74(0), 91-109. DOI: 10.1016/j.tra.2015.01.008.
Sander van Cranenburgh
Associate Professor
- +31 15 27 86957
- S.vanCranenburgh@tudelft.nl
-
Faculty of Technology, Policy and Management
Building 31Room: A3.210
Department:
Engineering Systems and Services
Group:
Transport and Logistics
Secretary:
Sabrina Bisschop
Research interests:
Travel Behaviour
Choice modelling
Large-scale travel demand models
Additional information
Ir. S. (Sander) van Cranenburgh
-
Biografie
I am assistant Professor of Choice modelling. My research aim is to develop new methods for enhancing our understanding of human choice behaviour. Understanding choice behaviour and being able to predict it is essential to the efficient functioning of society. For instance, it enables making appropriate provisions to accommodate travel demand when a new railway line is constructed, or when a new service is being introduced.
In my recent work I focus on new methods that bridge the gap between theory-driven discrete choice models and data-driven Artificial Intelligence (AI) models. Until recently, the discrete choice modelling field was almost exclusively based on theory-driven models. I try to push the frontier of this field by blending theory-driven discrete choice models with data-driven AI models. Doing so creates a whole new set of tools to investigate choice behaviour. Moreover, bringing together these modelling paradigms holds the potential to get the best of both: the flexibility and versatility of data-driven methods and the rigour and strong behavioural inference of theory-driven methods. See www.AI4ChoiceLab.com for the latest research on this fascinating topic by me and my co-workers.
In my Post-doc years (2013-2014) I have made a series of contributions to Random Regret Minimisation (RRM) based discrete choice models. RRM models are a behaviourally inspired counterpart of the classical Random Utility Maximisation model. I have developed: a new family of RRM models, new data collection methodology, and the world’s first RRM-based national transport model. See my personal website www.advancedRRMmodels.com for the latest developments in Random Regret Minimization (RRM) modelling, experimental design software for RRM models (Ngene & MATLAB), and estimation codes for RRM models for Biogeme (Bison, Python & Pandas), R (Apollo), MATLAB, and LatentGold Choice.
