Juan Acosta supports RSG’s travel forecasting work. His previous work has focused on understanding how transportation interacts with other critical infrastructure systems to better forecast human activity and mobility patterns. By combining transportation modeling with data science, Juan develops computational approaches that help clients analyze complex urban dynamics and design more efficient, resilient, and sustainable systems.
Juan’s expertise spans agent-based and activity-based modeling, as well as machine learning. His research has explored interdependencies between transportation and energy systems, the use of social media data to estimate telecommuting patterns, and the integration of artificial intelligence into urban forecasting models.
Based in Chicago, Juan enjoys cycling, long-distance running, playing the electric guitar, gaming, cooking, and discovering new anime and TV series.
Career Highlights
- Acosta-Sequeda, Juan; Verbas, Omer; Auld, Joshua and Derrible, Sybil, Interdependencies between Electricity Consumption and Transit and Their Potential to Forecast Transit Demand in Urban Settings. Available at SSRN: http://dx.doi.org/10.2139/ssrn.5227122 (Preprint)
- Acosta-Sequeda, J., Mohammadi, M., Patipati, S. et al. Estimating Telecommuting Rates in the USA Using Twitter Sentiment Analysis. Data Science for Transportation 6, 28 (2024). https://doi.org/10.1007/s42421-024-00114-0
- Acosta-Sequeda, Juan, Hevar Palani, Ali Movahedi, Aslihan Karatas, and Sybil Derrible. 2023. “Residential Electricity Consumption Patterns and Their Relationship to Commute Times by Mode.” Findings, September. https://doi.org/10.32866/001c.87940.
- Acosta-Sequeda J, Derrible S 2023 GTdownloader: A Python Package to Download, Visualize, and Export Georeferenced Tweets From the Twitter API. Journal of Open Research Software, 11: 7. DOI: https://doi.org/10.5334/jors.443
- Hevar Palani, Juan Acosta-Sequeda, Aslihan Karatas, Sybil Derrible, The role of socio-demographic and economic characteristics on energy-related occupant behavior, Journal of Building Engineering, Volume 75, 2023, 106875, ISSN 2352-7102, https://doi.org/10.1016/j.jobe.2023.106875.
- T.-T.-T. Ngo, H. T. Pham, J. G. Acosta, and S. Derrible, “Predicting bike-sharing demand using random forest,” Journal of Science and Transport Technology, vol. 22, pp. 13-21, May 20
Education
- PhD, Civil Engineering, University of Illinois Chicago
- MS, Transportation Engineering, National University of Colombia
- BS, Physics, National University of Columbia
Awards
- Received the 2024 American Public Transportation Foundation scholarship.
