Hasil untuk "Advertising"

Ben Xue, Dan Liu, Lixiang Wang et al.

Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires designs beyond large-language-model (LLM)-style training and serving recipes. We present a production-oriented generative recommender co-designed across architecture, learning, and serving, named GR4AD (Generative Recommendation for ADdvertising). As for tokenization, GR4AD proposes UA-SID (Unified Advertisement Semantic ID) to capture complicated business information. Furthermore, GR4AD introduces LazyAR, a lazy autoregressive decoder that relaxes layer-wise dependencies for short, multi-candidate generation, preserving effectiveness while reducing inference cost, which facilitates scaling under fixed serving budgets. To align optimization with business value, GR4AD employs VSL (Value-Aware Supervised Learning) and proposes RSPO (Ranking-Guided Softmax Preference Optimization), a ranking-aware, list-wise reinforcement learning algorithm that optimizes value-based rewards under list-level metrics for continual online updates. For online inference, we further propose dynamic beam serving, which adapts beam width across generation levels and online load to control compute. Large-scale online A/B tests show up to 4.2% ad revenue improvement over an existing DLRM-based stack, with consistent gains from both model scaling and inference-time scaling. GR4AD has been fully deployed in Kuaishou advertising system with over 400 million users and achieves high-throughput real-time serving.

Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta et al.

The growing use of foundation models (FMs) in real-world applications demands adaptive, reliable, and efficient strategies for dynamic markets. In the chemical industry, AI-discovered materials drive innovation, but commercial success hinges on market adoption, requiring FM-driven advertising frameworks that operate in-the-wild. We present a multilingual, multimodal AI framework for autonomous, hyper-personalized advertising in B2B and B2C markets. By integrating retrieval-augmented generation (RAG), multimodal reasoning, and adaptive persona-based targeting, our system generates culturally relevant, market-aware ads tailored to shifting consumer behaviors and competition. Validation combines real-world product experiments with a Simulated Humanistic Colony of Agents to model consumer personas, optimize strategies at scale, and ensure privacy compliance. Synthetic experiments mirror real-world scenarios, enabling cost-effective testing of ad strategies without risky A/B tests. Combining structured retrieval-augmented reasoning with in-context learning (ICL), the framework boosts engagement, prevents market cannibalization, and maximizes ROAS. This work bridges AI-driven innovation and market adoption, advancing multimodal FM deployment for high-stakes decision-making in commercial marketing.

Yukang Lin, Xiang Zhang, Shichang Jia et al.

Creative image in advertising is the heart and soul of e-commerce platform. An eye-catching creative image can enhance the shopping experience for users, boosting income for advertisers and advertising revenue for platforms. With the advent of AIGC technology, advertisers can produce large quantities of creative images at minimal cost. However, they struggle to assess the creative quality to select. Existing methods primarily focus on creative ranking, which fails to address the need for explainable creative selection. In this work, we propose the first paradigm for explainable creative assessment and selection. Powered by multimodal large language models (MLLMs), our approach integrates the assessment and selection of creative images into a natural language generation task. To facilitate this research, we construct CreativePair, the first comparative reasoning-induced creative dataset featuring 8k annotated image pairs, with each sample including a label indicating which image is superior. Additionally, we introduce Creative4U (pronounced Creative for You), a MLLMs-based creative selector that takes into account users' interests. Through Reason-to-Select RFT, which includes supervised fine-tuning with Chain-of-Thought (CoT-SFT) and Group Relative Policy Optimization (GRPO) based reinforcement learning, Creative4U is able to evaluate and select creative images accurately. Both offline and online experiments demonstrate the effectiveness of our approach. Our code and dataset will be made public to advance research and industrial applications.

Hongyu Chen, Min Zhou, Jing Jiang et al.

Creating advertising images is often a labor-intensive and time-consuming process. Can we automatically generate such images using basic product information like a product foreground image, taglines, and a target size? Existing methods mainly focus on parts of the problem and lack a comprehensive solution. To bridge this gap, we propose a novel product-centric framework for advertising image design called T-Stars-Poster. It consists of four sequential stages to highlight product foregrounds and taglines while achieving overall image aesthetics: prompt generation, layout generation, background image generation, and graphics rendering. Different expert models are designed and trained for the first three stages: First, a visual language model (VLM) generates background prompts that match the products. Next, a VLM-based layout generation model arranges the placement of product foregrounds, graphic elements (taglines and decorative underlays), and various nongraphic elements (objects from the background prompt). Following this, an SDXL-based model can simultaneously accept prompts, layouts, and foreground controls to generate images. To support T-Stars-Poster, we create two corresponding datasets with over 50,000 labeled images. Extensive experiments and online A/B tests demonstrate that T-Stars-Poster can produce more visually appealing advertising images.

Prashant Kumar Singh, Prashant Kumar Singh, Rupal Jain et al.

BackgroundIncreasing incidences of non-communicable diseases globally present a major public health challenge, with tobacco, alcohol, and ultra processed food products high in fat, sugar, and salt (HFSS) contributing significantly to this epidemic. Despite regulatory efforts, loopholes persist, allowing companies to promote such products through surrogate advertisements and new media platforms. This study investigates advertisements aired during the Men's Cricket World Cup 2023 on the Over-the-Top (OTT) platform.MethodsA comprehensive analysis of advertisements aired during the World Cup matches on OTT platform during October-November 2023 was undertaken to assess the extent and type of advertising of alcohol, tobacco and HFSS products. A standardized observation protocol was followed, documenting the frequency, type, and celebrity featured in each advertisement. The observed advertisements were categorized into six segments including surrogate tobacco and alcohol, soft drinks, energy drinks, edible products commonly consumed by children, and other edibles/beverages.ResultsObservations show that 80.9% (n = 1,769) of total advertisements promoted tobacco, alcohol and HFSS products. Notably, surrogate tobacco advertisements were predominantly displayed during matches involving the Indian team, accounting for 86.7% of the total surrogate tobacco advertisements. Edible products commonly consumed by children comprised 60.6% of unhealthy advertisements during over-breaks. Celebrity endorsements, particularly by Bollywood actors and Indian cricketers were common.ConclusionObservations reveal a concerning prevalence of advertisements promoting tobacco, alcohol, and HFSS products. Children emerged as a particularly vulnerable target for advertisement-induced consumption behaviors. These findings highlight the need for stricter regulations and effective enforcement to curb the promotion of unhealthy products.

Marijan Španer, Mitja Truntič, Darko Hercog

This article presents the development and implementation of an IoT-enabled, off-grid solar power supply prototype designed to power a range of electrical devices. The developed system comprises a Photovoltaic panel, a Maximum Power Point Tracking (MPPT) charger, a 2.5 kWh/24 V high-performance LiFePO4 battery bank with a Battery Management System, an embedded controller with IoT connectivity, and DC/DC and DC/AC converters. The PV panel serves as the primary energy source, with the MPPT controller optimizing battery charging, while the DC/DC and DC/AC converters supply power to the connected electrical devices. The article includes a case study of a developed platform for powering an information and advertising system. The system features a predictive energy management algorithm, which optimizes the appliance operation based on daily solar irradiance forecasts and real-time battery State-of-Charge monitoring. The IoT-enabled controller obtains solar irradiance forecasts from an online meteorological service via API calls and uses these data to estimate energy availability for the next day. Using this prediction, the system schedules and prioritizes the operations of connected electrical devices dynamically to optimize the performance and prevent critical battery discharge. The IoT-based controller is equipped with both Wi-Fi and an LTE modem, enabling communication with online services via wireless or cellular networks.

Xinyu Li

This paper explores how ad platforms can utilize Bayesian persuasion within blockchain-based auction systems to strategically influence advertiser behavior despite increased transparency. By integrating game-theoretic models with machine learning techniques and the principles of blockchain technology, we analyze the role of strategic information disclosure in ad auctions. Our findings demonstrate that even in environments with inherent transparency, ad platforms can design signals to affect advertisers' beliefs and bidding strategies. A detailed case study illustrates how machine learning can predict advertiser responses to different signals, leading to optimized signaling strategies that increase expected revenue. The study contributes to the literature by extending Bayesian persuasion models to transparent systems and providing practical insights for auction design in the digital advertising industry.

Yang Yang, Bo Chen, Chenxu Zhu et al.

Click-Through Rate (CTR) prediction is a fundamental technique for online advertising recommendation and the complex online competitive auction process also brings many difficulties to CTR optimization. Recent studies have shown that introducing posterior auction information contributes to the performance of CTR prediction. However, existing work doesn't fully capitalize on the benefits of auction information and overlooks the data bias brought by the auction, leading to biased and suboptimal results. To address these limitations, we propose Auction Information Enhanced Framework (AIE) for CTR prediction in online advertising, which delves into the problem of insufficient utilization of auction signals and first reveals the auction bias. Specifically, AIE introduces two pluggable modules, namely Adaptive Market-price Auxiliary Module (AM2) and Bid Calibration Module (BCM), which work collaboratively to excavate the posterior auction signals better and enhance the performance of CTR prediction. Furthermore, the two proposed modules are lightweight, model-agnostic, and friendly to inference latency. Extensive experiments are conducted on a public dataset and an industrial dataset to demonstrate the effectiveness and compatibility of AIE. Besides, a one-month online A/B test in a large-scale advertising platform shows that AIE improves the base model by 5.76% and 2.44% in terms of eCPM and CTR, respectively.

Yidan Xing, Zhilin Zhang, Zhenzhe Zheng et al.

Automated bidding, an emerging intelligent decision making paradigm powered by machine learning, has become popular in online advertising. Advertisers in automated bidding evaluate the cumulative utilities and have private financial constraints over multiple ad auctions in a long-term period. Based on these distinct features, we consider a new ad auction model for automated bidding: the values of advertisers are public while the financial constraints, such as budget and return on investment (ROI) rate, are private types. We derive the truthfulness conditions with respect to private constraints for this multi-dimensional setting, and demonstrate any feasible allocation rule could be equivalently reduced to a series of non-decreasing functions on budget. However, the resulted allocation mapped from these non-decreasing functions generally follows an irregular shape, making it difficult to obtain a closed-form expression for the auction objective. To overcome this design difficulty, we propose a family of truthful automated bidding auction with personalized rank scores, similar to the Generalized Second-Price (GSP) auction. The intuition behind our design is to leverage personalized rank scores as the criteria to allocate items, and compute a critical ROI to transform the constraints on budget to the same dimension as ROI. The experimental results demonstrate that the proposed auction mechanism outperforms the widely used ad auctions, such as first-price auction and second-price auction, in various automated bidding environments.

Eliran Abutbul, Yohay Kaplan, Naama Krasne et al.

With yearly revenue exceeding one billion USD, Yahoo Gemini native advertising marketplace serves more than two billion impressions daily to hundreds of millions of unique users. One of the fastest growing segments of Gemini native is dynamic-product-ads (DPA), where major advertisers, such as Amazon and Walmart, provide catalogs with millions of products for the system to choose from and present to users. The subject of this work is finding and expanding the right audience for each DPA ad, which is one of the many challenges DPA presents. Approaches such as targeting various user groups, e.g., users who already visited the advertisers' websites (Retargeting), users that searched for certain products (Search-Prospecting), or users that reside in preferred locations (Location-Prospecting), have limited audience expansion capabilities. In this work we present two new approaches for audience expansion that also maintain predefined performance goals. The Conversion-Prospecting approach predicts DPA conversion rates based on Gemini native logged data, and calculates the expected cost-per-action (CPA) for determining users' eligibility to products and optimizing DPA bids in Gemini native auctions. To support new advertisers and products, the Trending-Prospecting approach matches trending products to users by learning their tendency towards products from advertisers' sites logged events. The tendency scores indicate the popularity of the product and the similarity of the user to those who have previously engaged with this product. The two new prospecting approaches were tested online, serving real Gemini native traffic, demonstrating impressive DPA delivery and DPA revenue lifts while maintaining most traffic within the acceptable CPA range (i.e., performance goal). After a successful testing phase, the proposed approaches are currently in production and serve all Gemini native traffic.

Hanife Erişen, Fatma Nazlı Köksal

This study is interested in the persuasive and compelling modalities used by advertisers in political campaign advertising images, applied to persuade and impact their audiences. In this respect, this research focuses on two political campaigns posters, chosen by a non-random sampling procedure, commissioned by the Republic of Turkey current ruling party, and their main opposition, during the lead-up of the 2023 General Elections in Turkey. In this endeavour, a multimodal discourse analysis is utilised due to the study involving language and semiotic processes in a visual medium, serving as a foundation for the examination of the information gathered by Kress amp; van Leeuwen in 1996. In an effort to interpret the representational, interactional, and compositional meanings provided by the various parts of the chosen images, three metafunctions will be used. The results demonstrate that the visual grammar and multimodality-based theoretical framework may be adapted to the discourse of political advertisements. It was additionally found that the framework identified representational, interactional, and compositional processes, which contribute to the social interpretations of the images.

Francesco Pierri

Targeted advertising on online social platforms has become increasingly relevant in the political marketing toolkit. Monitoring political advertising is crucial to ensure accountability and transparency of democratic processes. Leveraging Meta public library of sponsored content, we study the extent to which political ads were delivered on Facebook and Instagram in the run up to 2022 Italian general election. Analyzing over 23 k unique ads paid by 2.7 k unique sponsors, with an associated amount spent of 4 M EUR and over 1 billion views generated, we investigate temporal, geographical, and demographic patterns of the political campaigning activity of main coalitions. We find results that are in accordance with their political agenda and the electoral outcome, highlighting how the most active coalitions also obtained most of the votes and showing regional differences that are coherent with the (targeted) political base of each group. Our work raises attention to the need for further studies of digital advertising and its implications for individuals' opinions and choices.

Johannes Hermle, Giorgio Martini

Ad platforms require reliable measurement of advertising returns: what increase in performance (such as clicks or conversions) can an advertiser expect in return for additional budget on the platform? Even from the perspective of the platform, accurately measuring advertising returns is hard. Selection and omitted variable biases make estimates from observational methods unreliable, and straightforward experimentation is often costly or infeasible. We introduce Asymmetric Budget Split, a novel methodology for valid measurement of ad returns from the perspective of the platform. Asymmetric budget split creates small asymmetries in ad budget allocation across comparable partitions of the platform's userbase. By observing performance of the same ad at different budget levels while holding all other factors constant, the platform can obtain a valid measure of ad returns. The methodology is unobtrusive and cost-effective in that it does not require holdout groups or sacrifices in ad or marketplace performance. We discuss a successful deployment of asymmetric budget split to LinkedIn's Jobs Marketplace, an ad marketplace where it is used to measure returns from promotion budgets in terms of incremental job applicants. We outline operational considerations for practitioners and discuss further use cases such as budget-aware performance forecasting.

Frigga Kruse

British mining and exploration companies were active in Spitsbergen, today Svalbard, between 1904 and 1953. This period was marked by events like the First World War and the signing of the Spitsbergen Treaty, some say Svalbard Treaty, and was therefore politically charged. This article investigates the British Arctic enterprise as portrayed in an influential newspaper, the London Times, where a diverse range of items appeared across the sections Advertising, Business, News, Editorials, and Letters to the Editor. Reports of the London Stock Exchange and the London Gazette serve as factual counterweights to potentially subjective media coverage. In four distinct phases, we see the archipelago’s emergence in global politics, post-war optimism until the settlement of all claim disputes in 1927, a quiet phase caused by global economic depression, and renewed but short-lived optimism after the Second World War. The paper concludes that the British Government took a stance in the Spitsbergen Question already in 1907, and the Times could not be instrumentalised to change this official political opinion. The study offers a baseline for new and comparative research using similar historical sources.

Zatonatska Tetiana, Dluhopolskyi Oleksandr, Artyukh Tatiana et al.

Today, the use of machine learning technology in combination with the use of big data are topics that are actively discussed in business around the world. This topic has long gone beyond the information sphere, as it now applies to almost every sphere of life: economic, telecommunications, education, medicine, administration, and especially defense. Predicting customer behavior based on scoring models is in its infancy in Ukrainian companies, the main ones being the introduction of artificial intelligence technologies and machine learning, which will be the leading catalyst that will facilitate decision-making in business in the nearest future. The aim of the study is to develop a scoring model that predicts the behavior of target segments, namely, updating their activity to activate advertising tools. To achieve the goal of the work a set of research methods was used: dialectical – to reveal the theoretical foundations of models and types of forecasting models; analytical – in the study of the functioning of the environment SAS, Anaconda; optimization methods – to choose the best model and generate features. Scientific novelty and theoretical significance lie in the development of a scoring model for predicting the activity of subscribers of the telecommunications company “VF Ukraine”, on the basis of which marketing campaigns are conducted. With the help of the built-in scoring model, the company “VF Ukraine” can target its campaigns to retain subscribers. The marketing directorate of the enterprise can choose the TOP-20 or TOP-30 of the most prone subscribers to non-resumption of activity, i.e., tend to switch to other mobile operators, and hold promotions for them – providing additional gifts and bonuses, money to mobile account.

Yongchun Zhu, Yudan Liu, Ruobing Xie et al.

In recommender systems and advertising platforms, marketers always want to deliver products, contents, or advertisements to potential audiences over media channels such as display, video, or social. Given a set of audiences or customers (seed users), the audience expansion technique (look-alike modeling) is a promising solution to identify more potential audiences, who are similar to the seed users and likely to finish the business goal of the target campaign. However, look-alike modeling faces two challenges: (1) In practice, a company could run hundreds of marketing campaigns to promote various contents within completely different categories every day, e.g., sports, politics, society. Thus, it is difficult to utilize a common method to expand audiences for all campaigns. (2) The seed set of a certain campaign could only cover limited users. Therefore, a customized approach based on such a seed set is likely to be overfitting. In this paper, to address these challenges, we propose a novel two-stage framework named Meta Hybrid Experts and Critics (MetaHeac) which has been deployed in WeChat Look-alike System. In the offline stage, a general model which can capture the relationships among various tasks is trained from a meta-learning perspective on all existing campaign tasks. In the online stage, for a new campaign, a customized model is learned with the given seed set based on the general model. According to both offline and online experiments, the proposed MetaHeac shows superior effectiveness for both content marketing campaigns in recommender systems and advertising campaigns in advertising platforms. Besides, MetaHeac has been successfully deployed in WeChat for the promotion of both contents and advertisements, leading to great improvement in the quality of marketing. The code has been available at \url{https://github.com/easezyc/MetaHeac}.

Luis Edwin Torres Paz, Juan Carlos Granados Barreto

En un mundo globalizado, regido por las tecnologías y comunicaciones, la realidad para la educación física es adversa, pues existe una gran brecha de desigualdad que ha dificultado su reinvención equilibrada e inclusiva en el ámbito virtual, a diferencia de lo ocurrido en otras áreas. Asimismo, en algunas instituciones ha desaparecido, en un momento en el que la mejora de los programas de educación física jugaría un papel importante en la prevención de trastornos mentales, el incremento de la salud física y la resiliencia en estudiantes, como lo afirma la Unesco (2019). También, en el Perú, en colegios con Bachillerato Internacional y particulares de elevado costo, las horas de educación física aumentaron, lo que evidencia el reconocimiento de su importancia para menguar el estrés, la ansiedad y el sedentarismo a mediano y largo plazos. Por tanto, se debe evaluar la situación mundial y peruana abordando el aspecto socioeconómico y la enseñanza de la educación física en el contexto de la pandemia y la globalización.

Chao Du, Zhifeng Gao, Shuo Yuan et al.

Modern online advertising systems inevitably rely on personalization methods, such as click-through rate (CTR) prediction. Recent progress in CTR prediction enjoys the rich representation capabilities of deep learning and achieves great success in large-scale industrial applications. However, these methods can suffer from lack of exploration. Another line of prior work addresses the exploration-exploitation trade-off problem with contextual bandit methods, which are recently less studied in the industry due to the difficulty in extending their flexibility with deep models. In this paper, we propose a novel Deep Uncertainty-Aware Learning (DUAL) method to learn CTR models based on Gaussian processes, which can provide predictive uncertainty estimations while maintaining the flexibility of deep neural networks. DUAL can be easily implemented on existing models and deployed in real-time systems with minimal extra computational overhead. By linking the predictive uncertainty estimation ability of DUAL to well-known bandit algorithms, we further present DUAL-based Ad-ranking strategies to boost up long-term utilities such as the social welfare in advertising systems. Experimental results on several public datasets demonstrate the effectiveness of our methods. Remarkably, an online A/B test deployed in the Alibaba display advertising platform shows an 8.2% social welfare improvement and an 8.0% revenue lift.

Iyad Batal, Akshay Soni

Multiple content providers rely on native advertisement for revenue by placing ads within the organic content of their pages. We refer to this setting as ``queryless'' to differentiate from search advertisement where a user submits a search query and gets back related ads. Understanding user intent is critical because relevant ads improve user experience and increase the likelihood of delivering clicks that have value to our advertisers. This paper presents Multi-Channel Sequential Behavior Network (MC-SBN), a deep learning approach for embedding users and ads in a semantic space in which relevance can be evaluated. Our proposed user encoder architecture summarizes user activities from multiple input channels--such as previous search queries, visited pages, or clicked ads--into a user vector. It uses multiple RNNs to encode sequences of event sessions from the different channels and then applies an attention mechanism to create the user representation. A key property of our approach is that user vectors can be maintained and updated incrementally, which makes it feasible to be deployed for large-scale serving. We conduct extensive experiments on real-world datasets. The results demonstrate that MC-SBN can improve the ranking of relevant ads and boost the performance of both click prediction and conversion prediction in the queryless native advertising setting.

Alessandro Nuara, Francesco Trovò, Nicola Gatti et al.

Pay-per-click advertising includes various formats (\emph{e.g.}, search, contextual, social) with a total investment of more than 200 billion USD per year worldwide. An advertiser is given a daily budget to allocate over several, even thousands, campaigns, mainly distinguishing for the ad, target, or channel. Furthermore, publishers choose the ads to display and how to allocate them employing auctioning mechanisms, in which every day the advertisers set for each campaign a bid corresponding to the maximum amount of money per click they are willing to pay and the fraction of the daily budget to invest. In this paper, we study the problem of automating the online joint bid/daily budget optimization of pay-per-click advertising campaigns over multiple channels. We formulate our problem as a combinatorial semi-bandit problem, which requires solving a special case of the Multiple-Choice Knapsack problem every day. Furthermore, for every campaign, we capture the dependency of the number of clicks on the bid and daily budget by Gaussian Processes, thus requiring mild assumptions on the regularity of these functions. We design four algorithms and show that they suffer from a regret that is upper bounded with high probability as O(sqrt{T}), where T is the time horizon of the learning process. We experimentally evaluate our algorithms with synthetic settings generated from real data from Yahoo!, and we present the results of the adoption of our algorithms in a real-world application with a daily average spent of 1,000 Euros for more than one year.