Learning the click-through rate for rare/new ads from similar ads

Dave, Kushal; Varma, Vasudeva

doi:10.1145/1835449.1835671

Cited by 50 publications

(27 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, previous studies [15,18,1,14,30,29,37,11] mainly focus on building a linear model based on features extracted from a query and its ads. On the other hand, the ad CTR prediction problem can be also formulated as a recommendation problem and collaborative filtering (CF) techniques can be applied [27].…”

Section: Related Workmentioning

confidence: 99%

“…The sparsity problem and the long tail distribution introduce intrinsic difficulties to obtaining accurate CTR prediction results. Previous studies tried to solve the sparsity problem by exploring the rich features of ads, queries, and their relationships [18,14,33]. The hierarchical information on ads is leveraged and collaborative filtering techniques are utilized to smooth the model [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting contextual factors for click modeling in sponsored search

Yin

Mei

Cao

et al. 2014

Proceedings of the 7th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Sponsored search is the primary business for today's commercial search engines. Accurate prediction of the Click-Through Rate (CTR) for ads is key to displaying relevant ads to users. In this paper, we systematically study the two kinds of contextual factors influencing the CTR: 1) In micro factors, we focus on the factors for mainline ads, including ad depth, query diversity, ad interaction. 2) In macro factors, we try to understand the correlations of clicks between organic search and sponsored search. Based on this data analysis, we propose novel click models which harvest these new explored factors. To the best of our knowledge, this is the first paper to examine and model the effects of the above contextual factors in sponsored search. Extensive experiments on large-scale real-world datasets show that by incorporating these contextual factors, our novel click models can outperform state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploiting contextual factors for click modeling in sponsored search

Yin

Mei

Cao

et al. 2014

Proceedings of the 7th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…Initially they have developed a keyword Bayesian networks using the [9] to predict the Click-Through Rate for rare or new ads. In this model the prediction was done for sponsored search ads.…”

Section: Literature Surveymentioning

confidence: 99%

Click Through Rate Prediction for Display Advertisement

Clemenshia¹,

Vijaya²

2016

IJCA

View full text Add to dashboard Cite

Computational Advertising is the currently emerging multidimensional statistical modeling sub-discipline in digital advertising industry. Web pages visited per user every day is considerably increasing, resulting in an enormous access to display advertisements (ads). The rate at which the ad is clicked by users is termed as the Click Through Rate (CTR) of an advertisement. This metric facilitates the measurement of the effectiveness of an advertisement. The placement of ads in appropriate location leads to the rise in the CTR value that influences the growth of customer access to advertisement resulting in increased profit rate for the ad exchange, publishers and advertisers. Thus it is imperative to predict the CTR metric in order to formulate an efficient ad placement strategy. This paper proposes a predictive model that generates the click through rate based on different dimensions of ad placement for display advertisements using statistical machine learning regression techniques such as multivariate linear regression (LR), poisson regression (PR) and support vector regression(SVR). The experiment result reports that SVR based click model outperforms in predicting CTR through hyperparameter optimization.

show abstract

“…These predictions are made using information about the ad from previous impressions of the ad [31]. For rare or new ads where such information is not available, information from semantically similar ads is used [16]. In both the cases, the relevance of ad to query can be used as one of the features to predict the click-through-rates.…”

Section: Ads Pipelinementioning

confidence: 99%

Interpreting Advertiser Intent in Sponsored Search

Vattikonda

Kodipaka

Zhou

et al. 2015

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Search engines derive revenue by displaying sponsored results along with organic results in response to user queries. In general, search engines run a per-query, on-line auction amongst interested advertisers to select sponsored results to display. In doing so, they must carefully balance the revenue derived from sponsored results against potential degradation in user experience due to less-relevant results. Hence, major search engines attempt to analyze the relevance of potential sponsored results to the user's query using supervised learning algorithms. Past work has employed a bag-of-words approach using features extracted from both the query and potential sponsored result to train the ranker.We show that using features that capture the advertiser's intent can significantly improve the performance of relevance ranking. In particular, we consider the ad keyword the advertiser submits as part of the auction process as a direct expression of intent. We leverage the search engine itself to interpret the ad keyword by submitting the ad keyword as an independent query and incorporating the results as features when determining the relevance of the advertiser's sponsored result to the user's original query. We achieve 43.2% improvement in precision-recall AUC over the best previously published baseline and 2.7% improvement in the production system of a large search engine.

show abstract

Learning the click-through rate for rare/new ads from similar ads

Cited by 50 publications

References 3 publications

Exploiting contextual factors for click modeling in sponsored search

Exploiting contextual factors for click modeling in sponsored search

Click Through Rate Prediction for Display Advertisement

Interpreting Advertiser Intent in Sponsored Search

Contact Info

Product

Resources

About