ICMC2022 @ Reykjavík, Iceland

We (I and two students, Haewon san and Keishi kun) participated in the 7th The International Choice Modelling Conference (ICMC 2022) held on May 23-25, 2022 in Reykjavik, Iceland (http://www.icmconference.org.uk/2022-icmc-reykjavik.html).

Conference venue
Conference venue

Keishi kun presented the work entitled Exploring the effects of response lag on model estimation results using a real-time context-aware stated preference survey data (Authors: Fujiwara, K., Varghese, V., Chikaraishi, M., Maruyama, T., Fujiwara, A.)

Haewon san presented the work entitled Capturing people’s perceived safety under a new transport environment with V2V and V2I communications based on a comparison of real and virtual experiences (Authors, Namgung, H., Chikaraishi, M., Fujiwara, A.)

Congratulations on Excellent jobs!

bar near the venue
bar near the venue

We also presented the following work: Fukuda, D., Chikaraishi, M., Nakagawa, S., Ono, T.: A unified survey and estimation framework for valuing travel time reliability. And, thankfully, there are two presentations citing our q-generalized logit (Nakayama & Chikaraishi, 2015; Chikaraishi & Nakayama, 2016). Thanks a lot, Fiore and Araki kun!

New Publication in Transportation Research Part C

The following paper is now available online:

Ishii, Y., Hayakawa, K., Koide, S., & Chikaraishi, M. (2022). Entropy Tucker model: Mining latent mobility patterns with simultaneous estimation of travel impedance parameters. Transportation Research Part C: Emerging Technologies, 137, 103559.


With the rapid increase in the availability of passive data in the field of transportation, combining machine learning with transportation models has emerged as an important research topic in recent years. This study proposes an entropy Tucker model that integrates (1) a Tucker decomposition technique, i.e., an existing machine learning method, and (2) an entropy maximizing model, i.e., an existing model used for modeling trip distribution in the field of transportation. In addition, an optimization algorithm is presented to empirically identify the proposed model. The proposed model provides a solid theoretical foundation for the machine learning method, substantially improves prediction performance, and provides richer behavioral implications through empirical parameter estimation of travel impedance. We conducted a case study using public transit smart card data. The results showed that the proposed model improves the prediction performance and interpretability of the results compared to the conventional nonnegative Tucker decomposition technique. Further, we empirically confirmed that the travel impedance varies with the origin–destination pair, time of the day, and day of the week. Finally, we discussed how embedding the theoretical foundations of transport modeling into machine learning methods can facilitate the use of various passive data in wider practical contexts of transport policy decision making.


New publication in Transportation Research Part C

The following paper is now available online:

Nakayama, S., Chikaraishi, M. (2021) Doubly generalized logit: a closed-form discrete choice model system with multivariate generalized extreme value distributed utilities, Transportation Research Part C, Vol. 132, 103315.

In this study, we generalize our previous q-generalized multinomial logit model (Nakayama & Chikaraishi, 2015), in which the heteroscedastic variance and flexible shape of the utility distribution are considered, by allowing for statistical dependency of alternatives. This is achieved by introducing the q-generalization of McFadden’s multivariate Gumbel distribution. Thus, the logit model is doubly generalized; 1) each utility follows the generalized extreme value distribution that includes the Gumbel, Weibull, and Fréchet distributions; and 2) the utility distribution is multivariate, and therefore, a nested or cross-nested structure and dependency of alternatives are allowed. The proposed doubly generalized logit model system allows for deriving new closed-form discrete choice models such as the q-generalized nested logit model and q-generalized cross-nested logit (CNL) model. Furthermore, the model system includes conventional logit models such as the multinomial logit, nested logit, and CNL models as special cases as well as the new generalized logit models, while retaining a closed-form expression. We empirically confirm that the goodness-of-fit of the proposed model could be substantially better compared to that of the conventional models in some cases, though the degree of improvements varies across cases.


Graduation: Maya Safira, Faisal Ali

Congratulations on your graduation, Maya Safira (Doctor course), Faisal Ali (Master course). Dr. Maya Safira is the very first PhD student from our lab. We really appreciate her hard work and efforts. Particularly, she made a great contribution to improving our ability as a team. We will try to keep your meme in our lab. Best wishes for both of your future!