Topics

This week’s assignments will guide you through the following topics:

• Agent based modeling
• Current practices for mode choice

Reading

Please read the following:

• Read Sections 3.1 of Activity-Based Travel Demand Models: A Primer
• Supplemental reading Mode Choice Analysis Using Random Forrest Decision Trees

Replication task

• Take a look at the heart dataset (HeartData_Full.csv) and make sure you can read it into a Jupyter notebook. We’ll talk about data cleaning next week, but feel free to take a first pass at exploring the data.
• You’ll eventually use the scikit-learn and xgboost libraries as you build your classification model in the coming weeks. Try to install both this week so we have to troubleshoot if necessary.

Tasks

Complete the following tasks:

1. Read the heart data into a notebook and take a pass at exploring the data

2. Download and install scikit-learn and xgboost if you don’t have them already

Weekly Questions

Answer the folowing questions on Canvas:

• What are some examples of discrete choices that we consider in a discrete-choice model within a travel demand model?
• What is random utility maximization? How are utilities for travel modes calculated? What are some advantages and disadvantages to this approach for mode selection?
• Why are nested models and composite utilities used in mode choice modeling?
• What is the difference between a trip and a tour in an activity-based model?