Back to DrivenData | Blog

Question about incorporating public data

I saw in a post that we may only use the 2019 data as public data. Does that mean we can’t use additional information, such as characteristics of neighborhoods (spatial location, crime history, etc…) or historical crimes rates in Baltimore/US that is publicly available on the internet?

You’re welcome to use other publicly available sources of data (and characteristics of neighborhoods is a good place to look). However, you cannot use other years of data from the same original data source as the 2019 data, or any derivatives of that data source. Any public data you use should be included in your algorithm write-ups.

If you have any questions about whether a given source is suitable, just reach out and we’ll let you know.