Etienne Côme
Research Subjects
Etienne Côme has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Latifa Oukhellou
Université Gustave Eiffel
7 shared publications - Cyprien Richer
France
2 shared publications - Mohamed Khalil El Mahrsi
France
2 shared publications Allou Samé
University Gustave Eiffel, COSYS, GRETTIA, Paris, France
1 shared publication- Allou Samé
COSYS-GRETTIA, Universit Gustave Eiffel, Marne-la-Valle, Champs-sur-Marne, France
1 shared publication - Anne-Christine Bronner1 shared publication
Latest Publications
- Open Access
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
The Impact of Telework on Local Consumption Evidence from Mobile Phone and Transaction Data
While previous studies examine the impact of telework on consumption either near residences or workplaces, the net effect on local demand remains unclear. Using high-frequency mobile phone and card transaction data from Lyon, France's second-largest metropolitan area, we identify two causal demand shocks: a 1pp increase in work-from-home presence raises local spending by 1%, and a 1pp decrease in workplace presence reduces spending by 1.3%. Aggregating these opposing effects, we find a small and statistically insignificant decline in weekday offline consumption, suggesting that most spending shifts from workplace to home. We find that working from home is associated with a moderate spatial shift of spending from urban cores to residential suburbs, and a slight sectoral reallocation from restaurants toward food retail and bars.
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessThe Impact of Telework on Local Consumption Evidence from Mobile Phone and Transaction Data
While previous studies examine the impact of telework on consumption either near residences or workplaces, the net effect on local demand remains unclear. Using high-frequency mobile phone and card transaction data from Lyon, France's second-largest metropolitan area, we identify two causal demand shocks: a 1pp increase in work-from-home presence raises local spending by 1%, and a 1pp decrease in workplace presence reduces spending by 1.3%. Aggregating these opposing effects, we find a small and statistically insignificant decline in weekday offline consumption, suggesting that most spending shifts from workplace to home. We find that working from home is associated with a moderate spatial shift of spending from urban cores to residential suburbs, and a slight sectoral reallocation from restaurants toward food retail and bars.
- Open Access
- 16 March 2026
- Published by Elsevier in Computers, Environment and Urban Systems
- Vol. 127
Improving the spatial distribution of secondary activities in synthetic populations through guidance forces
- 16 March 2026
- Published by Elsevier in Computers, Environment and Urban Systems
- Vol. 127
Open AccessImproving the spatial distribution of secondary activities in synthetic populations through guidance forces
- Open Access
- 13 March 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 186
Robust and reproducible evaluation framework for population synthesis models—Application to probabilistic and deep generative models
- 13 March 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 186
Open AccessRobust and reproducible evaluation framework for population synthesis models—Application to probabilistic and deep generative models
- Open Access
- 15 October 2025
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 202
Harmonizing dockless E-scooters: insights from Paris
- 15 October 2025
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 202
Open AccessHarmonizing dockless E-scooters: insights from Paris
- 19 October 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (3) , 330-345
How Has the Paris Rail Public-Transportation Network Recovered After the COVID-19 Pandemic? Applying a Mixture of Regressions Model
Through a combination of regulations, fear of contagion, and changes in travelers’ habits, the COVID-19 pandemic affected the mobility of public-transit ridership worldwide. To understand the longer-term effects of the pandemic on public-transit ridership, we focus on the case of Paris, France, thanks to an open 5 year record of entries into more than 500 stations. To deal with the large volume of data, we use a statistical model that performs clustering and segmentation simultaneously while incorporating many exogenous variables, such as the day of the week or lockdowns, to account for their effect on the number of entries. We carry out an in-depth analysis of the results for the segments and clusters. Examining and comparing the regression coefficients across clusters and consecutive segments allows us to draw per-cluster and per-segment conclusions. We show that the number of weekday trips decreased in most clusters and that the reduction in weekly variations is proportional to the share of weekday trips in the volume of entries before the pandemic. In addition, we characterize the changes in the weekly profile: Thursday was replaced by Tuesday as the day with the highest ridership; because of teleworking, Friday became the least crowded weekday in clusters with strong differences between weekdays and weekends, while the lowest ridership weekday remains Monday in the other clusters.
- 19 October 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (3) , 330-345
How Has the Paris Rail Public-Transportation Network Recovered After the COVID-19 Pandemic? Applying a Mixture of Regressions Model
Through a combination of regulations, fear of contagion, and changes in travelers’ habits, the COVID-19 pandemic affected the mobility of public-transit ridership worldwide. To understand the longer-term effects of the pandemic on public-transit ridership, we focus on the case of Paris, France, thanks to an open 5 year record of entries into more than 500 stations. To deal with the large volume of data, we use a statistical model that performs clustering and segmentation simultaneously while incorporating many exogenous variables, such as the day of the week or lockdowns, to account for their effect on the number of entries. We carry out an in-depth analysis of the results for the segments and clusters. Examining and comparing the regression coefficients across clusters and consecutive segments allows us to draw per-cluster and per-segment conclusions. We show that the number of weekday trips decreased in most clusters and that the reduction in weekly variations is proportional to the share of weekday trips in the volume of entries before the pandemic. In addition, we characterize the changes in the weekly profile: Thursday was replaced by Tuesday as the day with the highest ridership; because of teleworking, Friday became the least crowded weekday in clusters with strong differences between weekdays and weekends, while the lowest ridership weekday remains Monday in the other clusters.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (11) , 15687-15701
Deep Probabilistic Forecasting of Multivariate Count Data With “Sums and Shares” Distributions: A Case Study on Pedestrian Counts in a Multimodal Transport Hub
Forecasting counts data in transportation areas can enrich passenger information for public transport passengers, who may thus better plan their trips. Moreover, forecasting with uncertainty is particularly important in the transportation domain, where the risk of poorly managed high demand is to be avoided. In this paper, we propose a new probabilistic prediction model well-suited for multivariate, overdispersed, and possibly correlated count data. This model combines the strength of the deep learning framework with the modeling of counts data allowed by “sums and shares” distributions. Indeed, deep learning models can handle uncertainty by relying on an abstraction of contextual data and by assuming output distributions. Our model learns a latent representation of the input data with the help of a recurrent neural network and then translates it into multivariate count predictions with a sums and shares distribution, well suited to tackle multivariate overdispersed and correlated count data. An extensive benchmark of the proposed model is carried out. We compare this model with seven others from the state-of-the-art probabilistic forecasting models using five open-source data (bikes, taxis, railways, traffic, wikipedia) and a specific use case on pedestrian counts within a multimodal transport hub in the Paris Region. Our model outperforms other models in situations where the data present temporal regularities. The results also highlight the potential of our model in the specific use case. Moreover, this forecasting represents an interesting way to predict short-term pedestrian counts in response to different events, such as concerts or transport disruptions.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (11) , 15687-15701
Deep Probabilistic Forecasting of Multivariate Count Data With “Sums and Shares” Distributions: A Case Study on Pedestrian Counts in a Multimodal Transport Hub
Forecasting counts data in transportation areas can enrich passenger information for public transport passengers, who may thus better plan their trips. Moreover, forecasting with uncertainty is particularly important in the transportation domain, where the risk of poorly managed high demand is to be avoided. In this paper, we propose a new probabilistic prediction model well-suited for multivariate, overdispersed, and possibly correlated count data. This model combines the strength of the deep learning framework with the modeling of counts data allowed by “sums and shares” distributions. Indeed, deep learning models can handle uncertainty by relying on an abstraction of contextual data and by assuming output distributions. Our model learns a latent representation of the input data with the help of a recurrent neural network and then translates it into multivariate count predictions with a sums and shares distribution, well suited to tackle multivariate overdispersed and correlated count data. An extensive benchmark of the proposed model is carried out. We compare this model with seven others from the state-of-the-art probabilistic forecasting models using five open-source data (bikes, taxis, railways, traffic, wikipedia) and a specific use case on pedestrian counts within a multimodal transport hub in the Paris Region. Our model outperforms other models in situations where the data present temporal regularities. The results also highlight the potential of our model in the specific use case. Moreover, this forecasting represents an interesting way to predict short-term pedestrian counts in response to different events, such as concerts or transport disruptions.
- Open Access
greed: An R Package for Model-Based Clustering by Greedy Maximization of the Integrated Classification Likelihood
The greed package implements the general and flexible framework of arXiv:2002.11577 for model-based clustering in the R language. Based on the direct maximization of the exact Integrated Classification Likelihood with respect to the partition, it allows jointly performing clustering and selection of the number of groups. This combinatorial problem is handled through an efficient hybrid genetic algorithm, while a final hierarchical step allows accessing coarser partitions and extract an ordering of the clusters. This methodology is applicable in a wide variety of latent variable models and, hence, can handle various data types as well as heterogeneous data. Classical models for continuous, count, categorical and graph data are implemented, and new models may be incorporated thanks to S4 class abstraction. This paper introduces the package, the design choices that guided its development and illustrates its usage on practical use-cases.
Open Accessgreed: An R Package for Model-Based Clustering by Greedy Maximization of the Integrated Classification Likelihood
The greed package implements the general and flexible framework of arXiv:2002.11577 for model-based clustering in the R language. Based on the direct maximization of the exact Integrated Classification Likelihood with respect to the partition, it allows jointly performing clustering and selection of the number of groups. This combinatorial problem is handled through an efficient hybrid genetic algorithm, while a final hierarchical step allows accessing coarser partitions and extract an ordering of the clusters. This methodology is applicable in a wide variety of latent variable models and, hence, can handle various data types as well as heterogeneous data. Classical models for continuous, count, categorical and graph data are implemented, and new models may be incorporated thanks to S4 class abstraction. This paper introduces the package, the design choices that guided its development and illustrates its usage on practical use-cases.
- Open Access
- 1 January 2021
- Published by OpenEdition in Mappemonde
- Vol. 131
Le palmarès du Mapathon du colloque Tous (im)mobiles, tous cartographes ?
- 1 January 2021
- Published by OpenEdition in Mappemonde
- Vol. 131
Open AccessLe palmarès du Mapathon du colloque Tous (im)mobiles, tous cartographes ?
- Open Access
- 1 January 2019
- Published by OpenEdition in Cybergeo
Intermodal mobility analysis with smart-card data. Spatio-temporal analysis of the bus-metro network of Rennes metropole
This paper aims to analyse the intermodal practices of mobility in the bus-metro network of Rennes metropole. Intermodality being strongly linked to the use of urban public transport networks, the Rennes Métropole bus and metro network data provided by Keolis-Rennes provides a very significant part of daily intermodality. To compensate for the lack of information on destinations and correspondances in the ticketing data a reconstruction of trips was made on the basis of hypotheses provided by the literature. The research carried out in the "Mobilletic" project considerably deepened the understanding of the temporal and spatial dimensions of intermodal mobility within Rennes Métropole’s urban public transport network.daily mobility, public transport, data science, data analysis, intermodal transportation
- 1 January 2019
- Published by OpenEdition in Cybergeo
Open AccessIntermodal mobility analysis with smart-card data. Spatio-temporal analysis of the bus-metro network of Rennes metropole
This paper aims to analyse the intermodal practices of mobility in the bus-metro network of Rennes metropole. Intermodality being strongly linked to the use of urban public transport networks, the Rennes Métropole bus and metro network data provided by Keolis-Rennes provides a very significant part of daily intermodality. To compensate for the lack of information on destinations and correspondances in the ticketing data a reconstruction of trips was made on the basis of hypotheses provided by the literature. The research carried out in the "Mobilletic" project considerably deepened the understanding of the temporal and spatial dimensions of intermodal mobility within Rennes Métropole’s urban public transport network.daily mobility, public transport, data science, data analysis, intermodal transportation