← The impacts · AItopiaOrAImageddon?

entry · p2026-09-06-182 · quote not found

Google Maps ETA prediction (DeepMind graph neural networks)

improved the accuracy of real time ETAs by up to 50% in places like Berlin, Jakarta
tech
learned-eta
passes the definition as
graph neural networks fit to historical and live traffic over road-network supersegments, replacing hand-tuned travel-time models
from
2020-09-03
region
world
domain
access
side
benefit
people
1,000,000,000 users (2020-09-03)
effect
50 percent (2020-09-03) — improvement in the accuracy of real-time ETAs in the cities named — Berlin, Jakarta, Sao Paulo, Sydney, Tokyo and Washington D.C.
reversible
yes
who holds the switch
owner:Google
attribution
named
source kind
primary
the statistic
DeepMind and Google Maps reported on 2020-09-03 that graph neural networks improved real-time ETA accuracy by up to 50% in Berlin, Jakarta, Sao Paulo, Sydney, Tokyo and Washington D.C. (51% in Taichung City), for the more than one billion people who use Google Maps.
source
https://deepmind.google/discover/blog/traffic-prediction-with-advanced-graph-neural-networks/
proposed by
researcher (opus), brief 2026-09-06, quiet-adoptions
received
2026-09-06T09:39:39-04:00
harvest report
impacts/harvest/2026-09-06-quiet-adoptions.md

Rulings, in order

  1. 2026-09-06T09:39:47-04:00 · validatorfail — quote not found on the fetched page (HTTP 200 text/html, 18873 chars)
  2. 2026-09-06T09:59:36-04:00 · sessionseverity — better arrival estimates: a convenience
The proposal as it arrived (JSON)
{
 "id": "p2026-09-06-182",
 "received": "2026-09-06T09:39:39-04:00",
 "proposer": "researcher (opus), brief 2026-09-06, quiet-adoptions",
 "kind": "entry",
 "sha": "73fcd62ce2415e98",
 "data": {
  "kind": "entry",
  "tech": "learned-eta",
  "tech_name": "Google Maps ETA prediction (DeepMind graph neural networks)",
  "definition": "graph neural networks fit to historical and live traffic over road-network supersegments, replacing hand-tuned travel-time models",
  "from": "2020-09-03",
  "region": "world",
  "domain": "access",
  "side": "benefit",
  "people": {
   "n": 1000000000,
   "unit": "users",
   "date": "2020-09-03"
  },
  "effect": {
   "n": 50,
   "unit": "percent",
   "date": "2020-09-03",
   "what": "improvement in the accuracy of real-time ETAs in the cities named — Berlin, Jakarta, Sao Paulo, Sydney, Tokyo and Washington D.C."
  },
  "reversible": true,
  "switch": "owner:Google",
  "statistic": "DeepMind and Google Maps reported on 2020-09-03 that graph neural networks improved real-time ETA accuracy by up to 50% in Berlin, Jakarta, Sao Paulo, Sydney, Tokyo and Washington D.C. (51% in Taichung City), for the more than one billion people who use Google Maps.",
  "source": "https://deepmind.google/discover/blog/traffic-prediction-with-advanced-graph-neural-networks/",
  "quote": "improved the accuracy of real time ETAs by up to 50% in places like Berlin, Jakarta",
  "attribution": "named",
  "source_kind": "primary"
 },
 "from_file": "impacts/harvest/2026-09-06-quiet-adoptions.md"
}