Concept of Interactive Machine Learning in Urban Design Problems

  • Artem M. Chirkin ETH Zurich
  • Reinhard Koenig ETH Zurich


This work presents a concept of interactive machine learning in a human design process. An urban design problem is viewed as  a multiple-criteria optimization problem. The outlined feature  of an urban design problem is the dependence of a design  goal on a context of the problem. We model the design goal  as a randomized fitness measure that depends on the context.  In terms of multiple-criteria decision analysis (MCDA), the  defined measure corresponds to a subjective expected utility  of a user.  In the first stage of the proposed approach we let the algorithm  explore a design space using clustering techniques. The second  stage is an interactive design loop; the user makes a proposal,  then the program optimizes it, gets the user’s feedback and  returns back the control over the application interface.


Download data is not yet available.


Jonas Allegrini, Viktor Dorer, and Jan Carmeliet. 2015. Influence of morphologies on the microclimate in urban neighbourhoods. Journal of Wind Engineering and Industrial Aerodynamics 144 (sep 2015), 108–117. DOI:

Michel Avital and Dov Te’Eni. 2009. From generative fit to generative capacity: Exploring an emerging dimension of information systems design and task performance. In Information Systems Journal, Vol. 19. 345–367. DOI:

Liu Baoding and Chen Xiaowei. 2013. Uncertain Multiobjective Programming and Uncertain Goal Programming. Journal of Uncertainty Analysis and Applications (2013), 1–10.

M Batty. 2001. Exploring Isovist Fields: Space and Shape in Architectural and Urban Morphology. Environment and Planning B Planning and Design 28, 1 (2001), 123–150.

Wolfgang Ertel. 2012. Reinforcement learning combined with human feedback in continuous state and action spaces. In 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL). IEEE, 1–6. DOI:

Chris Fraley, Adrian E Raftery, Thomas Brendan Murphy, and Luca Scrucca. 2012. mclust Version 4 for R: Normal Mixture Modeling for Model-Based Clustering, Classification, and Density Estimation. (2012).

John Frazer. 2002. Creative Design and the Generative Evolutionary Paradigm. In Creative Evolutionary Systems. Elsevier, 253–274. DOI:

Klaus Hechenbichler and Klaus Schliep. 2004. Weighted k-Nearest-Neighbor Techniques and Ordinal Classification. Discussion Paper 399, SFB 386, Ludwig-Maximilians University Munich (2004).

Ralf Herbrich, Tom Minka, and Thore Graepel. 2007. TrueSkill: A Bayesian Skill Rating System. In NIPS. 569–576. DOI:

Bill Hillier and Julienne Hanson. 1984. The Social Logic of Space. Cambridge University Press, Cambridge. DOI:

Patrick Janssen. 2006. A generative evolutionary design method. Digital Creativity 17, 1 (2006), 49–63. DOI:

W. Bradley Knox and Peter Stone. 2015. Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance. Artificial Intelligence 225 (aug 2015), 24–50. DOI:

Murat Köksalan, Jyrki Wallenius, and Stanley Zionts. 2013. An Early History of Multiple Criteria Decision Making. Journal of Multi-Criteria Decision Analysis 20, 1-2 (jan 2013), 87–94. DOI:

Sivam Krish. 2011. A practical generative design method. Computer-Aided Design 43, 1 (jan 2011), 88–100. DOI:

Hang Li. 2011. Learning to Rank for Information Retrieval and Natural Language Processing. Synthesis Lectures on Human Language Technologies 4, 1 (apr 2011), 1–113. DOI:

F Mallor, Pedro M Mateo Collazos, Isolina Alberto Moralejo, and Carmen Azcárate Giménez. 2003. Multiobjective evolutionary algorithms: Pareto rankings. In VII Jornadas Zaragoza-Pau de Matem{á}tica Aplicada y estad{í}stica: Jaca (Huesca), 17-18 de septiembre de 2001. Prensas Universitarias de Zaragoza, 27–36.

Nikhil Naik, Jade Philipoom, Ramesh Raskar, and Cesar Hidalgo. 2014. Streetscore - Predicting the Perceived Safety of One Million Streetscapes. In CVPR Workshop on Web-scale Vision and Social Media. IEEE, 7. DOI:

Annibal Parracho Sant’Anna. 2015. Probabilistic Composition of Preferences, Theory and Applications. Springer International Publishing, Cham. DOI:

John Peponis, Jean Wineman, Mahbub Rashid, S Hong Kim, and Sonit Bafna. 1997. On the description of shape and spatial configuration inside buildings: convex partitions and their local properties. Environment and Planning B 24 (1997), 761–782.

Philip Salesses, Katja Schechtner, and César A. Hidalgo. 2013. The collaborative image of the city: mapping the inequality of urban perception. PLoS ONE 8, 7 (jan 2013). DOI:

Saba Saneinejad, Peter Moonen, and Jan Carmeliet. 2014. Comparative assessment of various heat island mitigation measures. Building and Environment 73 (mar 2014), 162–170. DOI:

Ben Shneiderman. 2003. Leonardo’s Laptop: Human Needs and the New Computing Technologies. (2003). DOI:

Vishal Singh and Ning Gu. 2012. Towards an integrated generative design framework. Design Studies 33, 2 (mar 2012), 185–207. DOI:

Yannis Sismanis. 2010. How I won the "Chess Ratings - Elo vs the Rest of the World" Competition. (dec 2010).

Alasdair Turner, Alan Penn, and Bill Hillier. 2005. An algorithmic definition of the axial map. Environment and Planning B: Planning and Design 32, 3 (2005), 425–444. DOI:

Ke Zhou, Gui-Rong Xue, Hongyuan Zha, and Yong Yu. 2008. Learning to rank with ties. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR ’08. ACM Press, New York, New York, USA, 275. DOI:

E. Zitzler and L. Thiele. 1999. Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Transactions on Evolutionary Computation 3, 4 (1999), 257–271. DOI:
How to Cite
CHIRKIN, Artem M.; KOENIG, Reinhard. Concept of Interactive Machine Learning in Urban Design Problems. International SERIES on Information Systems and Management in Creative eMedia (CreMedia), [S.l.], n. 2016/1, p. 1-8, july 2017. ISSN 2341-5576. Available at: <>. Date accessed: 29 feb. 2024.
Share |