Skip to content

Instantly share code, notes, and snippets.

@kemingy
Created January 5, 2019 06:08
Show Gist options
  • Select an option

  • Save kemingy/9d8b424d3ee5accfc8e26c00484b6db1 to your computer and use it in GitHub Desktop.

Select an option

Save kemingy/9d8b424d3ee5accfc8e26c00484b6db1 to your computer and use it in GitHub Desktop.
simple tips for computational advertising

Computational Advertising

  • Sponsored search
  • Contextual advertising
  • Display advertising

Pricing scheme

  • pay per click
  • pay per impression
  • pay per transaction

Chanllenges

  • short ad text

  • sparse queries (vocabulary mismatch)

  • noisy web content

  • no page rank

  • ad spam and click spam

  • opinionated content

  • dealing with new ads in ranking

Advertising Keywords

  • multi-label text classification
  • pattern based keyword extraction

Short Text in Ads for Contextual Advertising

  • topic modeling

Short Search Query for Sponsored Search

  • query substitution and rewriting

Ad Quality and Spam

  • determining ad quality
  • identifying click spam

Ranking

  • CTR prediction
  • learning to rank
  • collaborative filtering
  • hierarchies

User Behavior

  • profile based user targeting

Real Time Bidding

  • real time bidding
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment