While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem. Current benchmarks, however, are largely restricted to idealized simulations, failing to address the practical demands of specialized domains like advertising and marketing analytics. In these fields, tasks are inherently more complex, often requiring multi-round interaction with professional marketing tools. To address this gap, we propose AD-Bench, a benchmark designed based on real-world business requirements of advertising and marketing platforms. AD-Bench is constructed from real user marketing analysis requests, with domain experts providing verifiable reference answers and corresponding reference tool-call trajectories. The benchmark categorizes requests into three difficulty levels (L1-L3) to evaluate agents' capabilities under multi-round, multi-tool collaboration. Experiments show that on AD-Bench, Gemini-3-Pro achieves Pass@1 = 68.0% and Pass@3 = 83.0%, but performance drops significantly on L3 to Pass@1 = 49.4% and Pass@3 = 62.1%, with a trajectory coverage of 70.1%, indicating that even state-of-the-art models still exhibit substantial capability gaps in complex advertising and marketing analysis scenarios. AD-Bench provides a realistic benchmark for evaluating and improving advertising marketing agents, the leaderboard and code can be found at https://github.com/Emanual20/adbench-leaderboard.
Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to tokenize large-scale items into discrete sequences. Existing GR approaches predominantly generate SIDs via Residual Quantization (RQ), where items are encoded into embeddings and then quantized to discrete SIDs. However, this paradigm suffers from inherent limitations: 1) Objective misalignment and semantic degradation stemming from the two-stage compression; 2) Error accumulation inherent in the structure of RQ. To address these limitations, we propose UniSID, a Unified SID generation framework for generative advertisement recommendation. Specifically, we jointly optimize embeddings and SIDs in an end-to-end manner from raw advertising data, enabling semantic information to flow directly into the SID space and thus addressing the inherent limitations of the two-stage cascading compression paradigm. To capture fine-grained semantics, a multi-granularity contrastive learning strategy is introduced to align distinct items across SID levels. Finally, a summary-based ad reconstruction mechanism is proposed to encourage SIDs to capture high-level semantic information that is not explicitly present in advertising contexts. Experiments demonstrate that UniSID consistently outperforms state-of-the-art SID generation methods, yielding up to a 4.62% improvement in Hit Rate metrics across downstream advertising scenarios compared to the strongest baseline.
E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales). Keyphrases must be pertinent to items; otherwise, it can result in seller dissatisfaction and poor targeting -- towards that end relevance filters are employed. In this work, we describe the shortcomings of training relevance filter models on biased click/sales signals. We re-conceptualize advertiser keyphrase relevance as interaction between two dynamical systems -- Advertising which produces the keyphrases and Search which acts as a middleman to reach buyers. We discuss the bias of search relevance systems (middleman bias) and the need to align advertiser keyphrases with search relevance signals. We also compare the performance of cross encoders and bi-encoders in modeling this alignment and the scalability of such a solution for sellers at eBay.
In online advertising, advertisers commonly utilize auto-bidding services to bid for impression opportunities. A typical objective of the auto-bidder is to optimize the advertiser's cumulative value of winning impressions within specified budget constraints. However, such a problem is challenging due to the complex bidding environment faced by diverse advertisers. To address this challenge, we introduce ABPlanner, a few-shot adaptable budget planner designed to improve budget-constrained auto-bidding. ABPlanner is based on a hierarchical bidding framework that decomposes the bidding process into shorter, manageable stages. Within this framework, ABPlanner allocates the budget across all stages, allowing a low-level auto-bidder to bids based on the budget allocation plan. The adaptability of ABPlanner is achieved through a sequential decision-making approach, inspired by in-context reinforcement learning. For each advertiser, ABPlanner adjusts the budget allocation plan episode by episode, using data from previous episodes as prompt for current decisions. This enables ABPlanner to quickly adapt to different advertisers with few-shot data, providing a sample-efficient solution. Extensive simulation experiments and real-world A/B testing validate the effectiveness of ABPlanner, demonstrating its capability to enhance the cumulative value achieved by auto-bidders.
Internet live streaming is widely used in online entertainment and e-commerce, where live advertising is an important marketing tool for anchors. An advertising campaign hopes to maximize the effect (such as conversions) under constraints (such as budget and cost-per-click). The mainstream control of campaigns is auto-bidding, where the performance depends on the decision of the bidding algorithm in each request. The most widely used auto-bidding algorithms include Proportional-Integral-Derivative (PID) control, linear programming (LP), reinforcement learning (RL), etc. Existing methods either do not consider the entire time traffic, or have too high computational complexity. In this paper, the live advertising has high requirements for real-time bidding (second-level control) and faces the difficulty of unknown future traffic. Therefore, we propose a lightweight bidding algorithm Binary Constrained Bidding (BiCB), which neatly combines the optimal bidding formula given by mathematical analysis and the statistical method of future traffic estimation, and obtains good approximation to the optimal result through a low complexity solution. In addition, we complement the form of upper and lower bound constraints for traditional auto-bidding modeling and give theoretical analysis of BiCB. Sufficient offline and online experiments prove BiCB's good performance and low engineering cost.
P Pujiartini, Eko Priyo Purnomo, Ajree Ducol Malawani
Poverty has been one of the problems that are common among countries. If the government does not want debt to be more acute, then the government must place poverty alleviation as a priority. In making a poverty alleviation program, the government must consider the causes of poverty in an area. It will have different results when the application is implemented following the target program that is not on target. The empowerment of the poor through KUBE-FM is possible for the level of success. However, the failure rate to maintain group member solidarity is still high. Then the next challenge that must be faced by this KUBE group is industrial revolution 4.0, where all have implemented an automation system in production and advertising that uses the internet, such as internet media in marketing. In this study, the authors used an explorative qualitative method to find out the KUBE-FM Kuncara Lamb strategy in maintaining group and business solidarity in the Industrial Revolution 4.0 era. The author uses miles and Huberman’s concept to analyze the data, namely, reduction, display, and concluding. KUBE-FM strategy, Kuncara Lamb, maintains group solidarity, namely: managing group dynamics that members can be an example for everyone, transparency in the budget, and maintain honesty. In facing the era of automation and the internet of things, KUBE-FM Kuncara Lamb only relies on person-to-person advertising through friendship and seminars and hard work
The aim of this study is to examine the effects of influencer follower count and the presence of “common friends” on advertising effectiveness in PR posts. Previous research has shown that influencer marketing generates a greater advertising effect compared to celebrity endorsements, with follower count being a key factor. While prior studies have focused on quantitative aspects such as follower count, qualitative factors such as follower relationships have received less attention. This study examines the impact of Instagram’s “common friends” feature on advertising attitude and purchase intention. In Experiment 1, we found that PR posts with more followers of the influencer had significantly higher advertising attitudes and purchase intentions than PR posts with fewer followers. In Experiment 2, common friends were displayed, unlike in Experiment 1, and then PR posts by influencers with a small number of followers were found to have significantly higher advertising attitudes and purchase intentions than PR posts by influencers with a large number of followers.
The task of predicting conversion rates (CVR) lies at the heart of online advertising systems aiming to optimize bids to meet advertiser performance requirements. Even with the recent rise of deep neural networks, these predictions are often made by factorization machines (FM), especially in commercial settings where inference latency is key. These models are trained using the logistic regression framework on labeled tabular data formed from past user activity that is relevant to the task at hand. Many advertisers only care about click-attributed conversions. A major challenge in training models that predict conversions-given-clicks comes from data sparsity - clicks are rare, conversions attributed to clicks are even rarer. However, mitigating sparsity by adding conversions that are not click-attributed to the training set impairs model calibration. Since calibration is critical to achieving advertiser goals, this is infeasible. In this work we use the well-known idea of self-supervised pre-training, and use an auxiliary auto-encoder model trained on all conversion events, both click-attributed and not, as a feature extractor to enrich the main CVR prediction model. Since the main model does not train on non click-attributed conversions, this does not impair calibration. We adapt the basic self-supervised pre-training idea to our online advertising setup by using a loss function designed for tabular data, facilitating continual learning by ensuring auto-encoder stability, and incorporating a neural network into a large-scale real-time ad auction that ranks tens of thousands of ads, under strict latency constraints, and without incurring a major engineering cost. We show improvements both offline, during training, and in an online A/B test. Following its success in A/B tests, our solution is now fully deployed to the Yahoo native advertising system.
The exponential growth of the web and its benefits can be attributed largely to its open model where anyone with internet connection can access information on the web for free. This has created unprecedented opportunities for various members of society including the most vulnerable, as recognized by organizations such as the UN. This again can be attributed to online advertising, which has been the main financier to the open web. However, recent trends of paywalling information and services on the web are creating imminent dangers to such open model of the web, inhibiting access for the economically vulnerable, and eventually creating digital segregation. In this paper, we argue that this emerging model lacks sustainability, exacerbates digital divide, and might lead to collapse of online advertising. We revisit the ad-supported open web business model and demonstrate how global users actually pay for the ads they see. Using data on GNI (gross national income) per capita and average paywall access costs, we established a simple income-paywall expenditure gap baseline. With this baseline we show that 135 countries with a total population estimate of 6.56 billion people cannot afford a scenario of a fully paywalled web. We further discuss how a mixed model of the so-called "premium services" creates digital segregation and poses danger to online advertising ecosystem. Finally, we call for further research and policy initiatives to keep the web open and more inclusive with a sustainable business model.
In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the limited size and potential bias present in real-world datasets. This study presents and explores a generative augmentation framework of social network advertising data. Our framework explores three generative models for data augmentation - Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Gaussian Mixture Models (GMMs) - to enrich data availability and diversity in the context of social network advertising analytics effectiveness. By performing synthetic extensions of the feature space, we find that through data augmentation, the performance of various classifiers has been quantitatively improved. Furthermore, we compare the relative performance gains brought by each data augmentation technique, providing insights for practitioners to select appropriate techniques to enhance model performance. This paper contributes to the literature by showing that synthetic data augmentation alleviates the limitations imposed by small or imbalanced datasets in the field of social network advertising. At the same time, this article also provides a comparative perspective on the practicality of different data augmentation methods, thereby guiding practitioners to choose appropriate techniques to enhance model performance.
In this paper we study optimal advertising problems that models the introduction of a new product into the market in the presence of carryover effects of the advertisement and with memory effects in the level of goodwill. In particular, we let the dynamics of the product goodwill to depend on the past, and also on past advertising efforts. We treat the problem by means of the stochastic Pontryagin maximum principle, that here is considered for a class of problems where in the state equation either the state or the control depend on the past. Moreover the control acts on the martingale term and the space of controls can be chosen to be non-convex. The maximum principle is thus formulated using a first-order adjoint Backward Stochastic Differential Equations (BSDEs), which can be explicitly computed due to the specific characteristics of the model, and a second-order adjoint relation.
The scaling law is a notable property of neural network models and has significantly propelled the development of large language models. Scaling laws hold great promise in guiding model design and resource allocation. Recent research increasingly shows that scaling laws are not limited to NLP tasks or Transformer architectures; they also apply to domains such as recommendation. However, there is still a lack of literature on scaling law research in online advertisement retrieval systems. This may be because 1) identifying the scaling law for resource cost and online revenue is often expensive in both time and training resources for industrial applications, and 2) varying settings for different systems prevent the scaling law from being applied across various scenarios. To address these issues, we propose a lightweight paradigm to identify online scaling laws of retrieval models, incorporating a novel offline metric and an offline simulation algorithm. We prove that under mild assumptions, the correlation between the novel metric and online revenue asymptotically approaches 1 and empirically validates its effectiveness. The simulation algorithm can estimate the machine cost offline. Based on the lightweight paradigm, we can identify online scaling laws for retrieval models almost exclusively through offline experiments, and quickly estimate machine costs and revenues for given model configurations. We further validate the existence of scaling laws across mainstream model architectures (e.g., Transformer, MLP, and DSSM) in our real-world advertising system. With the identified scaling laws, we demonstrate practical applications for ROI-constrained model designing and multi-scenario resource allocation in the online advertising system. To the best of our knowledge, this is the first work to study identification and application of online scaling laws for online advertisement retrieval.
We present the results of an experiment documenting racial bias on Meta's Advertising Platform in Brazil and the United States. We find that darker skin complexions are penalized, leading to real economic consequences. For every \$1,000 an advertiser spends on ads with models with light-skin complexions, that advertiser would have to spend \$1,159 to achieve the same level of engagement using photos of darker skin complexion models. Meta's budget optimization tool reinforces these viewer biases. When pictures of models with light and dark complexions are allocated a shared budget, Meta funnels roughly 64\% of the budget towards photos featuring lighter skin complexions.
The purpose of this research was to examine the preferences of consumers for subcompact sedan cars in General Santos City, Philippines. This research may provide the car industry significant information as to how consumers process their car buying decisions that will in turn help car manufacturers and car dealerships develop market-driven marketing and sales strategies and tactics. Conjoint experimental research design was used in this study. Primary data were gathered through the use of a survey essentially structured using the orthogonally designed subcompact sedan car profiles that were rated by a total of 455 valid respondents based on their level of preference. Conjoint analysis revealed that consumers in General Santos City most prefer a subcompact sedan car which Price is USD. 16,044.00 (β=0.037), which Engine is 1.5 Liter - 4 Cylinder - 106 HP (β=0.092), which Safety feature is 6-7 SRS Airbags+Speed Sensing Doorlocks (β=0.019), which Fuel Efficiency is More than 12 Kilometers/Liter - City Driving (β=0.145) and which Brand is Honda - City (β=0.400). In addition, consumers place Brand as the most important attribute of a subcompact sedan car with overall relative importance of 43.065%, followed by Engine (18.898%), Price (17.088%), Fuel Efficiency (15.603%) and Safety (5.345%). Overall, majority of the consumers in General Santos City may choose Toyota - Vios as their Subcompact Sedan Car. This study recommends for car manufacturers to further nurture their car brands through advertising and other forms of promotion as consumers have the propensity to choose and purchase a subcompact sedan car primarily because of its brand.
Marketing. Distribution of products, Economics as a science