← The impacts · AItopiaOrAImageddon?

entry · p2026-09-06-010 · unverified

USPS handwritten address recognition (learned word recognisers, CEDAR/SUNY Buffalo)

25 billion letters a year are processed automatically by the US postal service
tech
usps-handwriting-recognition
passes the definition as
a lexicon-driven recogniser trained on scanned handwritten address images, reading destinations off real mail
from
1997
region
US
domain
access
side
benefit
people
25,000,000,000 letters per year (2009)
effect
— USD saved per year (2009) — letters bar-coded and sorted automatically instead of keyed by hand, saving hundreds of millions of dollars a year on a service everyone uses
reversible
yes
who holds the switch
owner:United States Postal Service
attribution
named
source kind
secondary
the statistic
Computing Community Consortium, 25 March 2009, quoted in the University at Buffalo record: using the learning-based system developed at SUNY Buffalo, 25 billion letters a year are processed automatically by the US Postal Service, saving hundreds of millions of dollars.
source
https://www.buffalo.edu/content/dam/www/research/pdf/Postal-Automation-Highlights_20160516.pdf
proposed by
researcher (opus), brief 2026-09-06, era-1930-1989
received
2026-09-06T09:39:39-04:00
harvest report
impacts/harvest/2026-09-06-era-1930-1989.md

Rulings, in order

  1. 2026-09-06T09:39:47-04:00 · validatorunverified — fetch failed: HTTP 403 text/html
The proposal as it arrived (JSON)
{
 "id": "p2026-09-06-010",
 "received": "2026-09-06T09:39:39-04:00",
 "proposer": "researcher (opus), brief 2026-09-06, era-1930-1989",
 "kind": "entry",
 "sha": "69e2a68bfbdfab8d",
 "data": {
  "kind": "entry",
  "tech": "usps-handwriting-recognition",
  "tech_name": "USPS handwritten address recognition (learned word recognisers, CEDAR/SUNY Buffalo)",
  "definition": "a lexicon-driven recogniser trained on scanned handwritten address images, reading destinations off real mail",
  "from": "1997",
  "region": "US",
  "domain": "access",
  "side": "benefit",
  "people": {
   "n": 25000000000,
   "unit": "letters per year",
   "date": "2009"
  },
  "effect": {
   "n": null,
   "unit": "USD saved per year",
   "date": "2009",
   "what": "letters bar-coded and sorted automatically instead of keyed by hand, saving hundreds of millions of dollars a year on a service everyone uses"
  },
  "reversible": true,
  "switch": "owner:United States Postal Service",
  "statistic": "Computing Community Consortium, 25 March 2009, quoted in the University at Buffalo record: using the learning-based system developed at SUNY Buffalo, 25 billion letters a year are processed automatically by the US Postal Service, saving hundreds of millions of dollars.",
  "source": "https://www.buffalo.edu/content/dam/www/research/pdf/Postal-Automation-Highlights_20160516.pdf",
  "quote": "25 billion letters a year are processed automatically by the US postal service",
  "attribution": "named",
  "source_kind": "secondary"
 },
 "from_file": "impacts/harvest/2026-09-06-era-1930-1989.md"
}