[thinkingemote]

They know where buses go usually, so if a point is going along a road that a bus isn't going on would be one idea. Another would be a flag identifying if a user has a car, and clustering of similar points together to identify a bus, also I imagine bus stops generate a pattern different subtle or obvious from normal traffic jam?

[Steltek]

But how is the article's wagon o' phones different from a bus? How does Google know if my 1 week old Google account has a car?

I just had another thought. The Boston area has been rolling out bus lanes and they're pretty fantastic. However, a crowded rush hour bus may have a perverse effect on their traffic jam calculations. Where normal cars will be at a stand still, Google will also see ~50 users absolutely flying down the road in comparison. What happens then?

[Forgeties79]

>How does Google know if my one week old Google account has a car?

I am being serious when I say this: they probably do. I get that comes off as “haha tongue in cheek we’re all being spied on amirite!?” but I imagine google can and does figure that stuff out very, very quickly. Plus most people aren’t just entering the google ecosystem for the first time with their new phone.

[thinkingemote]

Well I don't know, but I'd have a guess as to how they might easily do it. Pattern recognition and/or machine learning. Something like: here is what the pattern of a user moving through space when they are in a car. Here are a million other ones. Here is a pattern of a user walking through space, taking a bus, etc etc. Now here is an unknown user. What pattern of movement does this user match closest to?

A pattern would be, for example: is he ever seen moving more than 5mph? Does he use driving directions? Is he only seen moving faster along bus routes? If he is only seen along bus routes does his pattern of moving and stopping align with the bus stops? Is there usually traffic jams at the same time of the week on different days, etc.

Just build up a database of patterns and check a 1 week old account with that to see what it fits best.

Perhaps in an area with no predictable traffic and no bus routes, that a wagon of phone matches the pattern of a traffic jam caused by a blockage on a road. It's less likely to be a bus, perhaps?

[clord]

I expect a road is considered blocked up if its throughput has changed lower relative to normal. Normal bus traffic and normal car traffic don't trigger the alert, but if a wagon of phones rolls through very slow, that will sway the algo.

[jqr-]

It's unlikely that 50 users on a bus all have Google Maps open at the same time.

[Forgeties79]

Most people don’t disable background tracking or bother closing an app when they’re done with it, so while it’s unlikely all 50 are, it’s very possible many have had it open in the background for days (if not weeks).