TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

business enterprise

The Middle of the Results Page Became the Blind Spot

Randomized hotel listings show that shopping agents inspect deeper than people but retain a weak, non-monotonic position bias.

Published Updated Story ID: mp-2026-08-25-014
Read the complete editionStory JSON

Summary

Randomized hotel listings show that shopping agents inspect deeper than people but retain a weak, non-monotonic position bias.

Across 5,000 sessions and four language models, the middle of a 100-result page was least likely to be inspected—not the bottom. Position reached the choice stage for some models but not others, while all selected the same undominated listing; displayed attributes mattered more than rank.

Why it matters

Randomized hotel listings show that shopping agents inspect deeper than people but retain a weak, non-monotonic position bias.

Limits and context

  • Across 5,000 sessions and four language models, the middle of a 100-result page was least likely to be inspected—not the bottom.
  • Position reached the choice stage for some models but not others, while all selected the same undominated listing; displayed attributes mattered more than rank.

Key claims

  1. Randomized hotel listings show that shopping agents inspect deeper than people but retain a weak, non-monotonic position bias.

    Qualification: Across 5,000 sessions and four language models, the middle of a 100-result page was least likely to be inspected—not the bottom.

    Evidence: source-2026-08-25-014

Sources

  1. arXiv preprint 2608.22697arXiv · primary research

Corrections

No corrections have been recorded for this story.