Eren Manavoglu

Improving ad relevance in sponsored search

We describe a machine learning approach for predicting sponsored search ad relevance. Our baseline model incorporates basic features of text overlap and we then extend the model to learn from past user clicks on advertisements. We present a novel approach using translation models to learn user click propensity from sparse click logs. Our relevance predictions are then applied to multiple sponsored search applications in both offline editorial evaluations and live online user tests. The predicted relevance score is used to improve the quality of the search page in three areas: filtering low quality ads, more accurate ranking for ads, and optimized page placement of ads to reduce prominent placement of low relevance ads. We show significant gains across all three tasks.

Post-click conversion modeling and analysis for non-guaranteed delivery display advertising

In on-line search and display advertising, the click-trough rate (CTR) has been traditionally a key measure of ad/campaign effectiveness. More recently, the market has gained interest in more direct measures of profitability, one early alternative is the conversion rate (CVR). CVRs measure the proportion of certain users who take a predefined, desirable action, such as a purchase, registration, download, etc.; as compared to simply page browsing. We provide a detailed analysis of conversion rates in the context of non-guaranteed delivery targeted advertising. In particular we focus on the post-click conversion (PCC) problem or the analysis of conversions after a user click on a referring ad. The key elements we study are the probability of a conversion given a click in a user/page context, P(conversion | click, context). We provide various fundamental properties of this process based on contextual information, formalize the problem of predicting PCC, and propose an approach for measuring attribute relevance when the underlying attribute distribution is non-stationary. We provide experimental analyses based on logged events from a large-scale advertising platform.

Multimedia features for click prediction of new ads in display advertising

Non-guaranteed display advertising (NGD) is a multi-billion dollar business that has been growing rapidly in recent years. Advertisers in NGD sell a large portion of their ad campaigns using performance dependent pricing models such as cost-per-click (CPC) and cost-per-action (CPA). An accurate prediction of the probability that users click on ads is a crucial task in NGD advertising because this value is required to compute the expected revenue. State-of-the-art prediction algorithms rely heavily on historical information collected for advertisers, users and publishers. Click prediction of new ads in the system is a challenging task due to the lack of such historical data. The objective of this paper is to mitigate this problem by integrating multimedia features extracted from display ads into the click prediction models. Multimedia features can help us capture the attractiveness of the ads with similar contents or aesthetics. In this paper we evaluate the use of numerous multimedia features (in addition to commonly used user, advertiser and publisher features) for the purposes of improving click prediction in ads with no history. We provide analytical results generated over billions of samples and demonstrate that adding multimedia features can significantly improve the accuracy of click prediction for new ads, compared to a state-of-the-art baseline model.

The sum of its parts: reducing sparsity in click estimation with query segments

The critical task of predicting clicks on search advertisements is typically addressed by learning from historical click data. When enough history is observed for a given query-ad pair, future clicks can be accurately modeled. However, based on the empirical distribution of queries, sufficient historical information is unavailable for many query-ad pairs. The sparsity of data for new and rare queries makes it difficult to accurately estimate clicks for a significant portion of typical search engine traffic. In this paper we provide analysis to motivate modeling approaches that can reduce the sparsity of the large space of user search queries. We then propose methods to improve click and relevance models for sponsored search by mining click behavior for partial user queries. We aggregate click history for individual query words, as well as for phrases extracted with a CRF model. The new models show significant improvement in clicks and revenue compared to state-of-the-art baselines trained on several months of query logs. Results are reported on live traffic of a commercial search engine, in addition to results from offline evaluation.

Dynamic ad layout revenue optimization for display advertising

Display advertising has been growing rapidly in recent years, with revenue generated from display ads placed on spaces allocated on publishers web pages. Traditionally, the design and layout of ad spaces on a web page are predetermined and fixed for the publisher. The objective of this work is to investigate the revenue opportunities of changing the ad layout dynamically for the publisher. A dynamic ad layout revenue optimization framework is developed for display advertising, in terms of both guaranteed and non-guaranteed advertising. The system automatically selects the ad layout template with the highest potential revenue yield for each single web page presented to the user. Forecasting algorithms are developed to predict the revenue of each ad opportunity. Two objectives are explored for the forecasting algorithms of ad layout optimization, the expected revenue and actual revenue. Promising results are obtained in offline simulation on real data collected from a Yahoo! property. The dynamic ad layout optimization system is further tested on real-time traffic and a significant revenue gain is observed compared with a static ad layout serving method.