Sander van Cranenburgh is Associate Professor of Choice modelling. His research aim is to develop new methods for enhancing our understanding of human choice behaviour. In his recent work he focusses 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. Sander tries 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. 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.
Ahmad Alwosheel is a PhD candidate in the Transport and Logistics Group of the faculty of Technology Policy and Management of Delft University of Technology.
His research focuses on the synthesis between machine learning and discrete choice paradigm for choice behavior analysis. Before joining TU Delft, Ahmad worked for a joint research center between King Abdulaziz City for Science and Technology (KACST) and University of California San Diego (UCSD). He worked in the application of machine learning tools and internet of things (IoT) sensors at health related issues. Ahmad holds a master degree from University of Southern California in Electrical Engineering with concentration on digital signal processing in late 2014. During his master, he worked in applying machine learning and signal processing algorithms in audio diarization and speakers segmentation.
Jeroen Delfos is a PhD candidate of the Department of Engineering Systems and Services at the faculty of Technology Policy and Management at the TU Delft. Besides his PhD, Jeroen works as a data scientist at the Inspectorate of Justice and Security at the Ministry of Justice and Security.
Governments are increasingly confronted with the task to oversee the use of AI algorithms in the public domain. For instance, the Inspectorate of Justice and Security - which has the task to examine if organisations in the security and justice domain, like the Police and the Asylum and Migration agency, carry out their work correctly - is faced with the task to supervise the use of AI algorithms for police surveillance decisions. However, such oversight on AI algorithms in the public domain is currently in a pioneering stage. Jeroen's research aims to contribute to field by developing a framework for governments to supervise the use of AI algorithms in the Justice and Security domain.
José Ignacio Hernández is a Chilean PhD candidate of the Department of Engineering Systems and Services, section Transport and Logistics. He holds a Bachelor of Economics and a Master’s degree of Environmental and Natural Resource Economics of University of Concepción, Chile.
José Ignacio’s PhD project focuses on providing a better understanding on how citizens make choices about government-funded projects in the Participatory Value Evaluation (PVE) method. PVE is a novel framework for policy evaluation based on making citizens choose which projects should be conducted by the government. These choices can be based on different heuristics and decision rules, which implies that a conventional model that assumes pure utility-maximizer individuals may lead to incorrect predictions and inaccurate policy advices. To address this problem, Jose Ignacio will exploit AI to investigate the different decision rules that citizens use in PVE, and how their prevalence change on different experimental settings. This information will be used later to develop a theoretical framework that accounts for the prevalent decision rules that citizens hold when they make choices in PVE.
Marco is a part-time researcher at Delft University of Technology. He is also a Research Leader at Significance, an independent research institute specialised in quantitative research on mobility and transport. As a consultant, he has been involved in several large modelling projects (e.g. demand forecasting models for road, rail and air transport) and stated preference projects (both design and analysis).
Marco’s research strives to improve transport models. He is keen to explore new methods and has an eye for practical relevance. In his work he combines extensive in-the-field industry experience with an academic spirit to try the unexplored. Recently, he has been involved in the development of an Artificial Neural Networks based method to uncover the Value-of-Time distributions. Currently, he is pushing the envelope of this latter method further, and more generally aims to find out in what variety of ways ANNs can be used to improve or replace existing transport models.
Teodora Szép is a PhD candidate in the Transport and Logistics Group of the faculty of Technology Policy and Management of Delft University of Technology.
Teodora received her MSc degree in Economics at VU University Amsterdam. Her PhD research (which is part of the BEHAVE-program) focusses on modelling decision making with moral dimensions. To do so, she combines traditional choice models with AI. In particular, in her most recent work she analyses moral reasoning in texts written by decision-makers by employing Natural Language Processing techniques. The identified moral dimensions are, in turn, fed into a traditional choice model to predict moral choice behaviour.