FEATURE REQ: Intervention site prediction

[penrods]

Since we have access to the redacted anonymous data already from the city officials, we should be taking a step further and predicting the next predicted site, given the existing ones. Think of standard posterior estimation.

Officials might also be able to incorporate information into their modeling that is not publicly available, making this much better suited as a Healthcare Authority operation rather than a client-side calculation.

v2 could take it one step further by performing prediction on encrypted data from users directly

[gsecresearch]

I could build something for this. I'm just checking out this project for the first time, so I don't know how anything works currently. With some training data, I could see what the accuracy looks like to start with. I imagine that's not hosted here, though. Could someone with data access point me to somewhere to get started? Thanks.

[Ferrumofomega]

@penrods @gsecresearch We have access to these data already, if you're still interested @gsecresearch, I can grab it for you.

[gsecresearch]

@Ferrumofomega that sounds great. Let me know if I need to do anything for data access. Once I get a look, I can do some exploratory work and open a branch with some scripts for basic prediction. Will probably need some help on the interpretation of the data to flesh out the model further after that. Thanks!

[Ferrumofomega]

On it!