Bid Shading has become increasingly important in Online Advertising, with a large amount of commercial [4,12,13,29] and research work [11,20,28] recently published. Most approaches for solving the bid shading problem involve estimating the probability of win distribution, and then maximizing surplus [28]. These generally use parametric assumptions for the distribution, and there has been some discussion as to whether Log-Normal, Gamma, Beta, or other distributions are most effective [8,38,41,44]. In this paper, we show evidence that online auctions generally diverge in interesting ways from classic distributions. In particular, real auctions generally exhibit significant structure, due to the way that humans set up campaigns and inventory floor prices [16,26]. Using these insights, we present a nonparametric method for Bid Shading which enables the exploitation of this deep structure. The algorithm has low time and space complexity, and is designed to operate within the challenging millisecond Service Level Agreements of Real-Time Bid Servers. We deploy it in one of the largest Demand Side Platforms in the United States, and show that it reliably out-performs best in class Parametric benchmarks. We conclude by suggesting some ways that the best aspects of parametric and nonparametric approaches could be combined.

Since 2019, most ad exchanges and sell-side platforms (SSPs), in the online advertising industry, shifted from second to first price auctions. Due to the fundamental difference between these auctions, demand-side platforms (DSPs) have had to update their bidding strategies to avoid bidding unnecessarily high and hence overpaying. Bid shading was proposed to adjust the bid price intended for second-price auctions, in order to balance cost and winning probability in a first-price auction setup. In this study, we introduce a novel deep distribution network for optimal bidding in both open (non-censored) and closed (censored) online first-price auctions. Offline and online A/B testing results show that our algorithm outperforms previous state-of-art algorithms in terms of both surplus and effective cost per action (eCPX) metrics. Furthermore, the algorithm is optimized in run-time and has been deployed into VerizonMedia DSP as production algorithm, serving hundreds of billions of bid requests per day. Online A/B test shows that advertiser's ROI are improved by +2.4%, +2.4%, and +8.6% for impression based (CPM), click based (CPC), and conversion based (CPA) campaigns respectively.

Click-through rate (CTR) prediction is a crucial task in recommender systems and online advertising. The embedding-based neural networks have been proposed to learn both explicit feature interactions through a shallow component and deep feature interactions by a deep neural network (DNN) component. These sophisticated models, however, slow down the prediction inference by at least hundreds of times. To address the issue of significantly increased serving latency and high memory usage for real-time serving in production, this paper presents DeepLight: a framework to accelerate the CTR predictions in three aspects: 1) accelerate the model inference via explicitly searching informative feature interactions in the shallow component; 2) prune redundant parameters at the inter-layer level in the DNN component; 3) prune the dense embedding vectors to make them sparse in the embedding matrix. By combining the above efforts, the proposed approach accelerates the model inference by 46X on Criteo dataset and 27X on Avazu dataset without any loss on the prediction accuracy. This paves the way for successfully deploying complicated embedding-based neural networks in real-world serving systems.

Click-through rate (CTR) prediction plays a critical role in recommender systems and online advertising. The data used in these applications are multi-field categorical data, where each feature belongs to one field. Field information is proved to be important and there are several works considering fields in their models. In this paper, we proposed a novel approach to model the field information effectively and efficiently. The proposed approach is a direct improvement of FwFM, and is named Field-matrixed Factorization Machines (FmFM, or FM2). We also proposed a new explanation of FM and FwFM within the FmFM framework, and compared it with the FFM. Besides pruning the cross terms, our model supports field-specific variable dimensions of embedding vectors, which acts as a soft pruning. We also proposed an efficient way to minimize the dimension while keeping the model performance. The FmFM model can also be optimized further by caching the intermediate vectors, and it only takes thousands of floating-point operations (FLOPs) to make a prediction. Our experiment results show that it can out-perform the FFM, which is more complex. The FmFM model’s performance is also comparable to DNN models which require much more FLOPs in runtime.

Prospective display advertising poses a particular challenge for large advertising platforms. The existing machine learning algorithms are easily biased towards the highly predictable retargeting events that are often non-eligible for the prospective campaigns, thus exhibiting a decline in advertising performance. To that end, efforts are made to design powerful models that can learn from signals of various strength and temporal impact collected about each user from different data sources and provide a good quality and early estimation of users' conversion rates. In this study, we propose a novel deep time-aware approach designed to model sequences of users' activities and capture implicit temporal signals of users' conversion intents. On several real-world datasets, we show that the proposed approach consistently outperforms other, previously proposed approaches by a significant margin while providing interpretability of signal impact to conversion probability.

Online auctions play a central role in online advertising, and are one of the main reasons for the industry's scalability and growth. With great changes in how auctions are being organized, such as changing the second- to first-price auction type, advertisers and demand platforms are compelled to adapt to a new volatile environment. Bid shading is a known technique for preventing overpaying in auction systems that can help maintain the strategy equilibrium in first-price auctions, tackling one of its greatest drawbacks. In this study, we propose a machine learning approach of modeling optimal bid shading for non-censored online first-price ad auctions. We clearly motivate the approach and extensively evaluate it in both offline and online settings on a major demand side platform. The results demonstrate the superiority and robustness of the new approach as compared to the existing approaches across a range of performance metrics.

Conversion prediction plays an important role in online advertis- ing since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry. Unlike click pre- diction, conversions have different types in nature, and each type may be associated with different decisive factors. In this paper, we formulate conversion prediction as a multi-task learning problem, so that the prediction models for different types of conversions can be learned together. These models share feature representa- tions, but have their specific parameters, providing the benefit of information-sharing across all tasks. We then propose Multi-Task Field-weighted Factorization Machine (MT-FwFM) to solve these tasks jointly. Our experiment results show that, compared with two state-of-the-art models, MT-FwFM improve the AUC by 0.74% and 0.84% on two types of conversions, and the weighted AUC across all conversion types is also improved by 0.50%.

We analyze the causal effect of online ads on the conversion probability of the users who click on the ad (clickers). We show that designing a randomized experiment to find this effect is infeasible, and propose a method to find the local effect on the clicker conversions. This method is developed in the Potential Outcomes causal model, via Principal Stratification to model non-ignorable post-treatment (or endogenous) variables such as user clicks, and is validated with simulated data. Based on two large-scale randomized experiments, performed for 7.16 million users and 22.7 million users to evaluate ad exposures, a pessimistic analysis for this effect shows a minimum increase of the campaigns effect on the clicker conversion probability of 75% with respect to the non-clickers. This finding contradicts a recent belief that clicks are not indicative of campaign success, and provides guidance in the user targeting task. In addition, we find a larger number of converting users attributed to the overall campaign than those attributed based on the click-to-conversion (C2C) standard business model. This evidence challenges the well-accepted belief that C2C attribution model over-estimates the value of the campaign.

In this paper, we develop a time series approach, based on Dynamic Linear Models (DLM), to estimate the impact of ad impressions on the daily number of commercial actions when no user tracking is possible. The proposed method uses aggregate data, and hence it is simple to implement without expensive infrastructure. Specifically, we model the impact of daily number of ad impressions in daily number of commercial actions. We incorporate persistence of campaign effects on actions assuming a decay factor. We relax the assumption of a linear impact of ads on actions using the log-transformation. We also account for outliers with long-tailed distributions fitted and estimated automatically without a pre-defined threshold. This is applied to observational data post-campaign and does not require an experimental set-up. We apply the method to data from one commercial ad network on 2,885 campaigns for 1,251 products during six months, to calibrate and perform model selection. We set up a randomized experiment for two campaigns where user tracking is feasible. We find that the output of the proposed method is consistent with the results of A/B testing with similar confidence intervals.