Data science capstone domain of inquiry (DSC 180AB B05)
Developed by Alex Cloninger, Dan Baeder, Steve Hardy, Deloitte Team
This domain will investigate activity based travel demand moels. This domain also centers on feature extraction and model validation for speeding up such agent based models.
A critical element of a transportation demand model is the capability to estimate mode choice; the travel mode (drive alone, carpool, bike, transit, etc.) that each synthetic person uses to get from activity to activity. Correctly determining the distribution of modes in the model has implications for understanding the impact of any policy, land use, or infrastructure change over time.
A common approach to mode choice estimation is through use of a complex framework rooted in utility theory. This setup typically involves a multitude of features and associated coefficients, many of which likely have a negligible impact of mode choice determination but make constructing the model challenging. We will be investigating machine learning approaches to mode choice modeling that involves identifying only essential features and building a simplified model that can be more easily generalized and deployed. Some questions we wil be answering throughout this domain:
We will delve into this area via the following papers:
and replicate results in preparation for analysis of the travel mode choice data.
Participation in the weekly discussion section is mandatory. Each week, you are responsible for doing the reading/task assigned in the schedule. Come to section prepared to ask questions about and discuss the results of these tasks.
Each week, turn in answers to the weekly questions to Canvas. These questions are meant to focus your work for the week and help prepare you for discussion. If you have questions about your work, please ask them in section or office hours (I will rarely comment on your submission).
You are responsible for the entire weekly reading/task, even if portions are not covered in the weekly questions, as these are designed to help you in your replication. The weekly tasks are the building blocks for the project proposals/assignments due at the end of the quarter.
|Activity Based Travel Models
|Travel Mode Choice
|Tree Based Methods
|Final Model Building
|Ethics of Mobility Data
Friday 10-11am PT, same zoom link as course
See email to section for Zoom link
The Github page for this website that contains all needed code / data not specifically linked on the website is here: https://github.com/ACloninger/capstone-deloitte-travel-models
See email to section for link to join Slack channel