Not everyone has access to information that can improve their lives.

This information can be financial information, health information, legal advice, and crime levels.

Governments and policy makers don’t fully know the effects that legislation and policy changes can have on localities.

Can this be more accurately modeled?

Using shape files for Los Angeles county, zip codes, and census tracts, a geospatial cellular automata system was built and exercised to see how well it can predict changes to equity parameters. The effects of government policy changes or enhanced policing can now be predicted with reasonable accuracy.

Python was used to map demographics from the census tracts up to the zip code level. Each zipcode was a cell in the cellular automata model that then interacts with neighboring zipcodes. Running the model for a number of time periods gives one the natural trajectory of equity and demographic metrics. "Seeding in" an anticipated effect of a government policy change in a small geographic region was performed to see how the final state of the system compared with its natural trajectory. Additional parameters and cellular automata rules can be used to enhance the model behavior.

With additional data and experimentation, the model can serve as a tool to determine the effects of policy changes and other legislation or law enforcement action on areas of Los Angeles county.

Built With

Share this project:

Updates