Bid optimizing and inventory scoring in targeted online advertising

Perlich, Claudia; D'Alessandro, B; Hook, Rod; Stitelman, Ori; Raeder, Troy; Provost, Foster

doi:10.1145/2339530.2339655

Cited by 121 publications

(146 citation statements)

References 11 publications

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…After receiving a bid request from the exchange, M6D evaluates whether the consumer associated with the impression opportunity is a good prospect for a particular campaign, and if so, will submit a bid. The bid price is determined by a separate machine learning process, which is described elsewhere [16]. 1 If the M6D bid was the highest across all bids for this auction, M6D delivers an ad for the campaign.…”

Section: Background On M6d Display Advertising and Related Workmentioning

confidence: 99%

“…There are two reasons: drawing from P T involves actually winning-purchasing-randomly selected impressions in the bidding systems [16]. Moreover, these impressions must be purchased in a quantity that provides sufficient positive instances to estimate a reliable, high-quality model given the feature space X T .…”

Section: Transfer Learning For Display Advertisingmentioning

confidence: 99%

“…Each of these criteria may be approximated with a good ranking of potential purchasers in terms of their likelihood of purchasing. These problems have been described in detail previously [17,16,19]. A primary source of feature data is a consumer's browsing history, captured as a collection of anonymized (hashed) URLs that the consumer has visited in the past.…”

Section: Introductionmentioning

confidence: 99%

“…We are aware of only few existing papers in the machine learning literature that look critically under the hood at the anatomy and design choices of a real, deployed, massive-scale learning system, some of them for targeting advertisements (cf., [16,19]). Examining real, deployed learning systems can help to keep machine learning researchers aware of issues that are critical to the actual use of machine learning, and thereby can help to keep the science of machine learning vital [18].…”

Section: Introductionmentioning

confidence: 99%

“…Other aspects of the system have been presented previously in conference publications [16,17,19], and with few exceptions these will be treated quickly in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Machine learning for targeted display advertising: transfer learning in action

Perlich¹,

D'Alessandro²,

Raeder³

et al. 2013

Mach Learn

140

View full text Add to dashboard Cite

This paper presents a detailed discussion of problem formulation and data representation issues in the design, deployment, and operation of a massive-scale machine learning system for targeted display advertising. Notably, the machine learning system itself is deployed and has been in continual use for years, for thousands of advertising campaigns (in contrast to simply having the models from the system be deployed). In this application, acquiring sufficient data for training from the ideal sampling distribution is prohibitively expensive. Instead, data are drawn from surrogate domains and learning tasks, and then transferred to the target task. We present the design of this multistage transfer learning system, highlighting the problem formulation aspects. We then present a detailed experimental evaluation, showing that the different transfer stages indeed each add value. We next present production results across a variety of advertising clients from a variety of industries, illustrating the performance of the system in use. We close the paper with a collection of lessons learned from the work over half a decade on this complex, deployed, and broadly used machine learning system.

show abstract

Section: Background On M6d Display Advertising and Related Workmentioning

confidence: 99%

Section: Transfer Learning For Display Advertisingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Other aspects of the system have been presented previously in conference publications [16,17,19], and with few exceptions these will be treated quickly in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations