← Back to the feed
AI & softwareResearch findings

ACQ Framework for Automated Creative Quota Allocation in Large-Scale Advertising

Original published 2024.12.09 12:00 KSTAdded to Blackdeck 2026.10.25 06:29 KST

What has changed?

A two-stage framework efficiently predicts revenue under quota conditions and allocates creatives under capacity constraints.

Key points

  1. Increasing ad creatives from a single image improves bidding opportunities but leads to diminishing returns.
  2. ACQ predicts expected revenue under different quota conditions using a multi-task model on an unbalanced binary tree.
  3. Offline and online experiments on Kuaishur's platform show a 6.20% increase in advertising revenue.

Connect it to your work

Automatically optimizes creative quantity per image to maximize platform advertising revenue.

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivACQ: A Deployed Two-Stage Framework for Automated Creative Quota Allocation in Large-Scale Online Advertising