Modern digital advertising systems rely on two primary targeting mechanisms: keyword targeting, where advertisers manually specify search terms, and item-based targeting, which matches ads to buyer queries through semantic similarity. While both approaches are effective in isolation, they leave a coverage gap, particularly for broad queries and new items, where item-based targeting often underperforms. This paper presents a novel hybrid targeting framework that bridges this gap by transferring successful query–item associations from keyword targeting into item-based campaigns via semantic embeddings. Our method leverages historical query–item pairs to create robust query representations and applies similarity-driven transfer to expand the candidate query set for item-targeted ads. To balance coverage and quality, we introduce adaptive thresholding and evaluate multiple query selection strategies. Experimental results, including large-scale A/B tests on eBay's advertising platform, demonstrate that our approach significantly expands impression coverage for broad queries while maintaining relevance. The best-performing configuration selected a small set of high-quality queries per item combined with an adaptive relevance threshold, achieving over 5% incremental coverage while preserving click-through rate (CTR) and conversions-over-impression (CVI) performance. These findings highlight the effectiveness of combining the breadth of keyword targeting with the precision of item-based targeting, offering a scalable solution to the coverage gap in ad marketplaces.

The digital advertising field has always had challenging ML problems, learning from petabytes of data that is highly imbalanced, reactivity times in the milliseconds, and more recently compounded with the complex user's path to purchase across devices, across platforms, and even online/real-world behavior. The AdKDD workshop continues to be a forum for researchers in advertising, during and after KDD. Our website, which hosts slides and abstracts, continues to receive a large number of monthly visits and active users. In surveys during AdKDD 2019 and 2020, over 60% agreed that AdKDD is the reason they attended KDD, and over 90% indicated they would attend next year. The 2025 edition is particularly timely because of the increasing application of Graph-based NN and Generative AI models in advertising. Coupled with privacy-preserving initiatives, such as those enforced by GDPR or CCPA, the future of computational advertising is at an interesting crossroads. For this edition, we plan to solicit papers that span the spectrum of deep user understanding while remaining privacy-preserving. In addition, we will seek papers that discuss fairness in the context of advertising, to what extent does hyper-personalization work, and whether the ad industry as a whole needs to think through more effective business models such as incrementality. We have hosted several academic and industry luminaries as keynote speakers and have found our invited speaker series hosting expert practitioners to be an audience favorite. We will continue fielding a diverse set of keynote speakers and invited talks for this edition as well. As with past editions, we hope to motivate researchers in this space to think not only about the ML aspects but also to spark conversations about the societal impact of online advertising.

The digital advertising field has always had challenging ML problems, learning from petabytes of data that is highly imbalanced, reactivity times in the milliseconds, and more recently compounded with the complex user's path to purchase across devices, across platforms, and even online/real-world behavior. The AdKDD workshop continues to be a forum for researchers in advertising, during and after KDD. Our website which hosts slides and abstracts receives approximately 2,000 monthly visits and 1,800 active users during the KDD 2021. In surveys during AdKDD 2019 and 2020, over 60% agreed that AdKDD is the reason they attended KDD, and over 90% indicated they would attend next year. The 2024 edition is particularly timely because of the increasing application of Graph-based NN and Generative AI models in advertising. Coupled with privacy-preserving initiatives enforced by GDPR, CCPA the future of computational advertising is at an interesting crossroads. For this edition, we plan to solicit papers that span the spectrum of deep user understanding while remaining privacy-preserving. In addition, we will seek papers that discuss fairness in the context of advertising, to what extent does hyper-personalization work, and whether the ad industry as a whole needs to think through more effective business models such as incrementality. We have hosted several academic and industry luminaries as keynote speakers and have found our invited speaker series hosting expert practitioners to be an audience favorite. We will continue fielding a diverse set of keynote speakers and invited talks for this edition as well. As with past editions, we hope to motivate researchers in this space to think not only about the ML aspects but also to spark conversations about the societal impact of online advertising.

The digital advertising field has always had challenging ML problems, learning from petabytes of data that is highly imbalanced, reactivity times in the milliseconds, and more recently compounded with the complex user's path to purchase across devices, across platforms, and even online/real-world behavior. The AdKDD workshop continues to be a forum for researchers in advertising, during and after KDD. Our website which hosts slides and abstracts receives approximately 2,000 monthly visits and 1,800 active users during the KDD 2021. In surveys during AdKDD 2019 and 2020, over 60% agreed that AdKDD is the reason they attended KDD, and over 90% indicated they would attend next year. The 2023 edition is particularly timely because of the increasing application of Graph-based NN and Generative AI models in advertising. Coupled with privacy-preserving initiatives enforced by GDPR, CCPA the future of computational advertising is at an interesting crossroads. For this edition, we plan to solicit papers that span the spectrum of deep user understanding while remaining privacy-preserving. In addition, we will seek papers that discuss fairness in the context of advertising, to what extent does hyper-personalization work, and whether the ad industry as a whole needs to think through more effective business models such as incrementality. We have hosted several academic and industry luminaries as keynote speakers and have found our invited speaker series hosting expert practitioners to be an audience favorite. We will continue fielding a diverse set of keynote speakers and invited talks for this edition as well. As with past editions, we hope to motivate researchers in this space to think not only about the ML aspects but also to spark conversations about the societal impact of online advertising.

An average consumer spends 8+ hours a day across all devices interacting with online content almost entirely sponsored by advertisements. At over $450B global market size in 2022 and expected to pass $1T by 2027, online advertising has already surpassed traditional ads in global spend. Moreover, computational advertising in particular is perhaps the most visible and ubiquitous application of machine learning and one that interacts directly with consumers. When done right, ads help us enrich our lives and creep us out when done badly. Looking at the published literature over the last few years, many researchers might consider computational advertising as a mature field. Yet, the opposite is true. The field is evolving, however, from ads controlled by monolithic publishers and randomly rotating banner ads to highly personalized content experiences in news feeds on mobile devices and even on TV-all utilizing data amassed from petabytes of stored user data. Ads are far from done.

The digital advertising field has always had challenging ML problems, learning from petabytes of data that is highly imbalanced, reactivity times in the milliseconds and more recently compounded with the complex user's path to purchase across devices, across platforms and even online/real-world behavior. The AdKDD workshop continues to be a forum for researchers in advertising, during and after KDD. Our website which hosts slides and abstracts receives approximately 2,000 monthly visits. In surveys during AdKDD 2019 and 2020, over 60% agreed that AdKDD is the reason they attended KDD and over 90% indicated they would attend next year. The 2021 edition is particularly timely because of ongoing developments in ad tracking. We will aim to discuss notions of privacy and tracking enforced by GDPR and through company policies. In addition, we will seek papers that discuss fairness in the context of advertising, to what extent does hyper-personalization work, and on whether the ad industry as a whole needs to think through more effective business models such as incrementality. Ad tech is in an interesting place of evolution/maturity now and we would like to use the AdKDD forum to get the researchers to think not only about the ML aspects but also spark conversations about the societal ones.

Understanding what interests and delights users is critical to effective behavioral targeting, especially in information-poor contexts. As users interact with content and advertising, their passive behavior can reveal their interests towards advertising. Two issues are critical for building effective targeting methods: what metric to optimize for and how to optimize. More specifically, we first attempt to understand what the learning objective should be for behavioral targeting so as to maximize advertiser's performance. While most popular advertising methods optimize for user clicks, as we will show, maximizing clicks does not necessarily imply maximizing purchase activities or transactions, called conversions, which directly translate to advertiser's revenue. In this work we focus on conversions which makes a more relevant metric but also the more challenging one. Second is the issue of how to represent and combine the plethora of user activities such as search queries, page views, ad clicks to perform the targeting. We investigate several sources of user activities as well as methods for inferring conversion likelihood given the activities. We also explore the role played by the temporal aspect of user activities for targeting, e.g., how recent activities compare to the old ones. Based on a rigorous offline empirical evaluation over 200 individual advertising campaigns, we arrive at what we believe are best practices for behavioral targeting. We deploy our approach over live user traffic to demonstrate its superiority over existing state-of-the-art targeting methods.

In contextual advertising advertisers show ads to users so that they will click on them and eventually purchase a product. Optimizing this action sequence, called the conversion funnel, is the ultimate goal of advertising. Advertisers, however, often have very different sub-goals for their ads such as purchase, request for a quote, or simply a site visit. Often an improvement for one advertiser's goal comes at the expense of others. A single ranking function must balance these different goals in order to make an efficient system for all advertisers. We propose a ranking method that globally balances the goals of all advertisers, while simultaneously improving overall performance. Our method has been shown to improve significantly over the baseline in online traffic at a major ad network.

An important step in the quest for low-cost fusion power is the ability to perform and analyze experiments in prototype fusion reactors. One of the tasks in the analysis is the classification of orbits in Poincaré plots generated by the particles in a fusion reactor as they move within the toroidal device. In this paper, we describe the use of graph-based methods to extract features from orbits. These features are then used to classify the orbits into several categories. Our results show that existing machine learning algorithms are successful in classifying orbits with few points, a situation which can arise in data from experiments.

Adaptive clustering uses external feedback to improve cluster quality; past experience serves to speed up execution time. An adaptive clustering environment is proposed that uses Q-learning to learn the reward values of successive data clusterings. Adaptive clustering supports the reuse of clusterings by memorizing what worked well in the past. It has the capability of exploring multiple paths in parallel when searching for good clusters. In a case study, we apply adaptive clustering to instance-based learning relying on a distance function modification approach. A distance function adaptation scheme that uses external feedback is proposed and compared with other distance function learning approaches. Experimental results indicate that the use of adaptive clustering leads to significant improvements of instance-based learning techniques, such as k-nearest neighbor classifiers. Moreover, as a by-product a new instance-based learning technique is introduced that classifies examples by solely using cluster representatives; this technique shows high promise in our experimental evaluation.