Скачать презентацию What is Computational Advertising Transparency and value Скачать презентацию What is Computational Advertising Transparency and value

b9612eab06af8cf383e27681bf076b56.ppt

  • Количество слайдов: 167

What is “Computational Advertising”? What is “Computational Advertising”?

Transparency and value Transparency and value

Extract Topical info Increases coverage, more relevant match Extract Topical info Increases coverage, more relevant match

Precision Recall 25% lift in precision at 10% recall Precision Recall 25% lift in precision at 10% recall

Retrospective data [URL, ad, is. Clicked] Crawl URLs a sample of URLs Classify pages Retrospective data [URL, ad, is. Clicked] Crawl URLs a sample of URLs Classify pages and ads Rare event estimation using hierarchy Impute impressions, fix sampling bias

Retrospective data [page, ad, isclicked] Crawl Pages a sample of pages Classify pages and Retrospective data [page, ad, isclicked] Crawl Pages a sample of pages Classify pages and ads Rare event estimation using hierarchy Impute impressions, fix sampling bias

Unobserved “state” Unobserved “state”

om d TS an R S LM , N om d TS an R S LM , N

Bandit “arms” (unknown payoff probabilities) Bandit “arms” (unknown payoff probabilities)

Bandit “arms” (unknown payoff probabilities) Bandit “arms” (unknown payoff probabilities)

Priority 1 Priority 2 Priority 3 Priority 1 Priority 2 Priority 3

Bandit “arms” = ads Bandit “arms” = ads

One bandit Unknown CTR Content Match = A matrix One bandit Unknown CTR Content Match = A matrix

Root Apparel Computers Travel Page/Ad Root Apparel Computers Travel Page/Ad

…… … … …… Consider only two levels …… … … …… Consider only two levels

Ad parent classes Ad child classes …… … … …… Consider only two levels Ad parent classes Ad child classes …… … … …… Consider only two levels Block One bandit

Ad parent classes Ad child classes …… … … …… Block One bandit Ad parent classes Ad child classes …… … … …… Block One bandit

? ?

ad ? ad ?

ad ad

# clicks in cell # impressions in cell All cells in a block come # clicks in cell # impressions in cell All cells in a block come from the same distribution

Estimated CTR Beta prior (“block CTR”) Observed CTR Estimated CTR Beta prior (“block CTR”) Observed CTR

Root 20 nodes … 221 nodes ~7000 leaves Taxonomy structure We use these 2 Root 20 nodes … 221 nodes ~7000 leaves Taxonomy structure We use these 2 levels

Clicks Number of pulls Multi-level gives much higher #clicks Clicks Number of pulls Multi-level gives much higher #clicks

Number of pulls Mean-Squared Error Number of pulls Mean-Squared Error

Mean-Squared Error Clicks Number of pulls Mean-Squared Error Clicks Number of pulls