Prepare
Due: August 29, 2024
Learning objectives
- Assess competing interests in defining the objectives of a predictive model
- Evaluate the impact of model decisions on stakeholders
- Identify potential sources of bias in a predictive model
- Describe the role of transparency in model development
Preparations
📖 Read
Automated valuation model for all class 200 residential properties in Cook County
This is the documentation for a machine learning model used by the Cook County (Illinois) Assessor’s Office to predict the value of residential properties. The model is used to determine property assessments which are used for determining property tax rates. The documentation provides a high-level overview of the model, including its purpose, data sources, and evaluation metrics. You do not need to run any code in the repository. Instead, read the sections on “Model Overview”, “Ongoing Issues”, and “FAQs”. Be prepared to discuss the model and development workflow in class.
⌨️ Do (if you have not already):
- Log in to Cornell’s GitHub at https://github.coecis.cornell.edu/. You already have an account created based on your Cornell NetID.
- One of the following:
Access RStudio Workbench using your Cornell NetID and password
Click the “New Session” button on the top of the page. Leave all the settings on their default state and click “Start Session”. If this is your first time accessing RStudio Workbench for the course, it may take a couple of minutes to prepare your session. Please be patient. When you start a session in the future, your container will already be prepared and it should start within 15 seconds.