[HN Gopher] Event-level prediction of urban crime reveals a enfo... ___________________________________________________________________ Event-level prediction of urban crime reveals a enforcement bias in US cities Author : darkscape Score : 29 points Date : 2022-07-02 18:33 UTC (4 hours ago) (HTM) web link (www.nature.com) (TXT) w3m dump (www.nature.com) | mdp2021 wrote: | We discussed this same article one day ago at | https://news.ycombinator.com/item?id=31941781 | s1artibartfast wrote: | In other fields, this is called triage. Some communities are | bleeding profusely and police can only temporarily stem the | symptoms because the root cause is much deeper. In other | communities, quick intervention can stabilize the situation | point_blank wrote: | Locked to the public. Sci-hub does not have the document either. | mastercheif wrote: | Found it here: | https://www.researchgate.net/publication/349228599_Precise_E... | balderdash wrote: | Wow this thing is impossible to decipher | samatman wrote: | That's because the product of value to the 'researchers' is | the title. | abduhl wrote: | " These precise predictions enable equally precise evaluation of | inequities in law enforcement, discovering that response to | increased crime rates is biased by the socio-economic status of | neighborhoods, draining policy resources to wealthy areas with | disproportionately negative impacts for the inner city, as | demonstrated in Chicago and six other major U.S. metropolitan | areas." | | In other words, cops abandon poor neighborhoods when crime goes | up there and mobilize to rich neighborhoods when crime goes up | there. I'd be interested to know the other 6 metro areas, | although I have a suspicion of which ones they are and their | flavor of DA. | ezekiel11 wrote: | Korean immigrants found that out the hard way almost 30 years | ago in LA. | bergenty wrote: | No they knew. It's just that riots don't happen that often so | they were willing to take the risk and the opportunity cost | since other Americans wouldn't do it. | civilized wrote: | So, they fit a fancy model, played with it, and claim the result | says something about the real world? | | I have never seen a valid social science result derived by this | method. This is just fancy model lovers dabbling. | | If the patterns they claim are real, they can be exposed with | much simpler and direct methods. Let's talk after that's been | done. | mulmen wrote: | What are those simpler and direct methods? Have they been done? | bergenty wrote: | Is fancy supposed to be derogatory in this statement? | civilized wrote: | Too fancy for anyone to be confident in what it's doing or | whether it reflects real patterns. | | 0.90 AUC doesn't mean everything you can get this model to | tell you is real. ___________________________________________________________________ (page generated 2022-07-02 23:00 UTC)