Google ad delivery algorithm showed gender bias in high paying job advertisements

A 2015 study by Carnegie Mellon University found that Google's ad delivery system showed significantly fewer high-paying job advertisements to women than to men. Researchers used simulated profiles to demonstrate that gender was the primary factor in this disparity.

Google · Incident Jul 1, 2015 · Indexed Jun 9, 2026 · 3 sources

Male users were shown high-paying job ads about 1,800 times, compared to female users who saw those ads about 300 times.
What
A 2015 study by Carnegie Mellon University found that Google's ad delivery system showed significantly fewer high-paying job advertisements to women than to men.
Incident date
Jul 1, 2015
Who
Google
Failure mode
Policy Violation
AI surface
Recommender
Severity
Medium

What happened

Research from Carnegie Mellon University revealed that Google's advertising system exhibited gender bias in the delivery of high-paying job ads. In one experiment, a career coaching service for executive jobs paying over $200,000 was shown 1,852 times to male profiles but only 318 times to female profiles. The findings suggested that this algorithmic behavior could potentially widen the gender pay gap.

What broke inside the model

Failure path · mode profile · Policy Violation
  1. 01 · TriggerA prompt pushes against a deployment boundary.
  2. 02 · Model stepThe model produces the disallowed output.
  3. 03 · Control gapNo enforcement blocks it at generation time.
  4. 04 · FailureThe output crosses the policy line.
  5. 05 · ConsequenceA limit the business set is breached in public.

The output crosses a policy boundary the deployment had defined.

The failure stemmed from an opaque ad-targeting mechanism that used profiling and machine learning to deliver ads. While the specific internal weights were not public, the system produced discriminatory outcomes despite users having identical browsing behaviors and fresh profiles, with gender being the only differing variable.

Public visibilityHigh
Regulatory exposureNone
Customer impactMany customers
Financial impactUnknown
Time to disclosureHours
  1. PressWomen less likely to be shown ads for high-paid jobs on Google, study showstheguardian.com
  2. PrimaryFewer Women Than Men Are Shown Online Ads Related to High-Paying Jobscsd.cmu.edu
  3. PressGoogle's algorithm shows prestigious job ads to men, but not to womenwashingtonpost.com
Permalinkhttps://failureindex.ai/failures/google-delivery-algorithm-showed-gender-bias
CitationAI Failure Index. "Google ad delivery algorithm showed gender bias in high paying job advertisements" (FI-0373). Realm Labs. https://failureindex.ai/failures/google-delivery-algorithm-showed-gender-bias (indexed Jun 9, 2026).
Share cardA branded image of this record for posts and slides.

Data fields CC-BY 4.0, prose citation permitted. Incident ID FI-0373. Full dataset at /data.

Note from Realm Labs, the Index steward

How Realm fits

Controls for this failure mode
  • Prism
  • OmniGuard

This entry sits in the index's predictive wing: a system that scores, ranks, perceives, or steers rather than generates. Realm's runtime layer is built for the generative and agentic systems now moving into these same decision seats, where it watches a model's internal state and holds an unsupported claim or an unchecked action before it commits. The control gap on this record, an automated decision that reached people with no runtime check in front of it, is the same gap. The index keeps predictive failures on the record because the pattern carries straight into the systems shipping today.