Hi! I’m trying to understand how are the naics codes assigned to the core poi. From the documentation it seems like SafeGraph uses a category algorithm. Does anyone know what are the steps in that algorithm? Thanks
This topic was automatically generated from Slack. You can find the original thread here.
Hi Niki, thanks for the link. do you know if its possible to learn more about the details of this process? Some precise questions I have are for example: 1)does safegraph look into open source information about all POI or just some? if it’s only for a subset of the POI, how are the POIs selected? 2) how are the long tail POIs defined? Thanks again
Hi - thanks for the additional details. I’m not super knowledgable on the details of this process. However, I’m happy to loop in someone from our Product team to get you specifics. We’ll get back to you with updates once I hear from them. Thanks, Nathalie!
Hi ! In response to your two questions outlined above:
1.) We look at open source POI info where it’s available and conflate that with POI data obtained from other sources. Open source data is most useful for non-consumer types of places, like parks and museums, whereas closed/commercial sources are most useful for consumer-focused locations like a bank or a Starbucks.
2.) “longtail” means any POI that is not a part of a common brand/banner name.
Hi ! Just confirming that we answered your question. I’m going to go ahead and close this thread out. If you have any more questions or follow-up questions, we’re always here to help! Just be sure to make a new post to safegraphdata, as we aren’t monitoring old threads at this time. Thanks!