Today’s Cache | How Amazon uses feedback from video reviewers to train algorithms?

Amazon uses feedback from video reviewers to train its warehouse-monitoring algorithms

November 22, 2022 04:55 pm | Updated 08:19 pm IST

File photo of people arriving for work at the Amazon distribution center in the Staten Island borough of New York

File photo of people arriving for work at the Amazon distribution center in the Staten Island borough of New York | Photo Credit: AP

(This article is part of Today’s Cache, The Hindu’s newsletter on emerging themes at the intersection of technology, innovation and policy. To get it in your inbox, subscribe here.)

Amazon is using offshore workers based in India and Costa Rica to review camera footage from its warehouses to train its monitoring algorithms, a report from The Verge shared.

The feedback from video reviewers is used by Amazon to train its AI camera system that monitors the stowing process in its warehouses. This camera reportedly also tracks the stower’s movements and sends footage to video reviewers whose inputs help the company improve its machine learning tools.

Published in partnership with the Bureau of Investigative Journalism, the report stated that workers reviewing footage from warehouses are paid just hundreds of dollars a month for eight-hour shifts that can be extended to 11 hours during busy periods. During shifts, reviewers can get through 8,000 videos every day.

Reviewers working on warehouse monitoring complained of physical problems including headaches, eye pain, and eyesight deterioration. They also complained that they were made to meet difficult targets, with tracking software logging in periods of inactivity outside their designated break time.

These reviewers watch footage from cameras stationed in warehouses that monitor stower’s movements.

Video reviewers shared that their primary role was to stock management, however, they can also record errors made by their colleagues overseas.

Managers also keep track of reviewers’ performance with real-time analytics and maintain an accuracy rate of 95-99%.

Reviewers who are unable to maintain high accuracy at a fast pace risk losing their jobs.

Reviewers are rated based on their “TAKT” time, the average time to get through a video with those ranking in the last four places highlighted in red, according to a document shared by a former reviewer.

The report also shared that most workers being filmed in warehoused by Amazon’s cameras were unaware that they were being watched and that their footage could be sent to manual reviewers.

Amazon on its part stated that its system algorithm monitoring stower’s is 95% accurate and only the remainder of it requires a manual check. It also stated that a number of allegations made in the report were based on anecdotes from a handful of individuals and painted a misleading picture that does not represent the majority of its team.

The company also shared that reviewers in India and Costa Rica were encouraged by the software they use to take short breaks throughout their shifts.

The report is based on interviews spanning 33 current and former Amazon employees, including 21 video reviewers.

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in

Comments

Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.