Exploiting contextual factors for click modeling in sponsored search

Abstract

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.

Examining the Impact of Keyword Ambiguity on Search Advertising Performance: A Topic Model Approach

“…This might cause consumers to be dissatisfied with the organic search results, and they may turn to sponsored ads and look for an alternative that meets their needs. This substitution effect has also been suggested by prior studies that examined the relationship between the organic results and sponsored ads (Jansen and Resnick 2006;Buscher et al 2010;Jerath et al 2014;Yin et al 2014). Prior literature has shown that most consumers examine organic results first before sponsored ads (Jansen and Resnick 2006).…”

“…One of the gaps in the existing literature is the interplay between organic and sponsored search results (Jansen and Resnick 2006;Jansen et al 2007;Buscher et al 2010;Danescu-Niculescu-Mizil et al 2010;Agarwal et al 2015;Yin et al 2014). Earlier experimental studies have shown that most consumers examine organic results first before sponsored ads (Jansen and Resnick 2006;Jansen et al 2007), but the relevance ratings for organic results and those for sponsored ads are practically the same (Jansen 2007).…”

“…An eye tracking study by Buscher et al (2010) finds that, when a list of less relevant ads is displayed, the organic results receive more visual attention. Using data from a commercial search engine, Yin et al (2014) examine the correlation between the CTR of organic results and the CTR of sponsored ads and find a negative correlation between the two types of search results. In addition, Agarwal et al (2015) analyze click-through and conversion data from an online retailer using a hierarchical Bayesian model and find that the competitive intensity in the organic listing has a negative impact on the click performance of sponsored ads, suggesting a substitution effect between the organic listing and sponsored listing.…”

Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction

“…Xiong et al [29] consider the pairwise relationship between ads shown on the same page and propose a Conditional Random Field (CRF)-based model for CTR prediction. Yin et al [30] consider various contextual factors such as ad depth, query diversity and ad interaction for click modeling. One major problem of these models is that the vertex and edge feature functions need to be manually defined based on data analysis and it is difficult to generalize the model to other types of data.…”

Click Through Rate Prediction for Display Advertisement

“…The regression model was derived using gradient boosted decision trees (GBDT) and the click information of semantically related ads. Dawei Yin et al, put forward a model [5] based on the contextual factors for click modeling in sponsored search. Using these contextual factors that are explored they had presented the click model for sponsored search.…”