A Unified Solution to Constrained Bidding in Online Display Advertising

He, Yong; Chen, Xiujun; Wu, Di; Pan, Junwei; Tan, Qing; Yu, Chuan; Xu, Jian; Zhu, Xiaoqiang

doi:10.1145/3447548.3467199

Cited by 29 publications

(36 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to these work that exploit the monotonicty of budget, some works propose to deal with specific non-monotonic constraints [14,35,39] or general constraints [16,32]. Among them, a promising solution [16,32] adopts a soft combination design that softly combines the constraint violations and the delivery value in the objective function with extra trade-off parameters, theoretically grounded by Lagrangian relaxation to achieve a balanced constraint-objective trade-off. These works, however, are typically established in controlled markets, where market dynamics change smoothly as each ad campaign binds to similar types of impressions, and full access to market information can be gained 2 .…”

Section: Problem Statementmentioning

confidence: 99%

“…While this reward function design appears simple, it renders a parameter-free solution to accommodate constraints, by setting a hard barrier between feasible and infeasible solutions. The underlying philosophy is that, we designate feasibility to weigh heavier than infeasibility in rewards, instead of softly combining the constraint violations and delivery value as adopted in soft combination algorithms [16,32]. Soft combination solutions are ambiguous in reflecting the quality of different solutions, especially when the trade-off parameters are inappropriate.…”

Section: A Semi Impression-level Policy To Deal With Long Sequencesmentioning

confidence: 99%

“…To this end, the proposed hard barrier solution bears no extra parameters for hand-tuning (c.f. USCB [16]), and performs adaptive control in non-stationary ad markets even with out-of-distribution (OOD) data (Sec. 4.4).…”

Section: 24mentioning

confidence: 99%

“…2). Recent approaches [16,32] handles the constraint-objective trade-off by soft combination algorithms, which introduce extra trade-off parameters to softly combine constraint violations and objective value in the objective functions. Despite their promising results, these methods assume static or mildly changing markets, which are limited in the more non-stationary markets.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning

Wang,

Du,

Fang

et al. 2022

Preprint

View full text Add to dashboard Cite

Real-Time Bidding (RTB) is an important mechanism in modern online advertising systems. Advertisers employ bidding strategies in RTB to optimize their advertising effects subject to various financial requirements, especially the return-on-investment (ROI) constraint. ROIs change non-monotonically during the sequential bidding process, and often induce a see-saw effect between constraint satisfaction and objective optimization. While some existing approaches show promising results in static or mildly changing ad markets, they fail to generalize to highly dynamic ad markets with ROI constraints, due to their inability to adaptively balance constraints and objectives amidst non-stationarity and partial observability. In this work, we specialize in ROI-Constrained Bidding in non-stationary markets. Based on a Partially Observable Constrained Markov Decision Process, our method exploits an indicator-augmented reward function free of extra trade-off parameters and develops a Curriculum-Guided Bayesian Reinforcement Learning (CBRL) framework to adaptively control the constraint-objective trade-off in non-stationary ad markets. Extensive experiments on a large-scale industrial dataset with two problem settings reveal that CBRL generalizes well in both in-distribution and out-of-distribution data regimes, and enjoys superior learning efficiency and stability.

show abstract

Section: Problem Statementmentioning

confidence: 99%

Section: A Semi Impression-level Policy To Deal With Long Sequencesmentioning

confidence: 99%

Section: 24mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning

Wang,

Du,

Fang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Bid optimization is one of the most fundamental problems in online advertising [6,18,37,40,41]. Recently, bid shading [11,20,42] attracts much attention since most ad exchanges and SSPs are shifting from second to first price auctions.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions

Zhou

Pan

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

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. CCS CONCEPTS• Applied computing → Online auctions; • Information systems → Display advertising; • Computing methodologies → Machine learning algorithms.

show abstract

Keyword-Level Bayesian Online Bid Optimization for Sponsored Search Advertising

Majima,

Kawakami,

Ishizuka

et al. 2024

Oper. Res. Forum

View full text Add to dashboard Cite

Bid price optimization in online advertising is a challenging task due to its high uncertainty. In this paper, we propose a bid price optimization algorithm focused on keyword-level bidding for pay-per-click sponsored search ads, which is a realistic setting for many firms. There are three characteristics of this setting: “The setting targets the optimization of bids for each keyword in pay-per-click sponsored search advertising”, “The only information available to advertisers is the number of impressions, clicks, conversions, and advertising cost for each keyword”, and “Advertisers bid daily and set monthly budgets on a campaign basis”. Our algorithm first predicts the performance of keywords as a distribution by modeling the relationship between ad metrics through a Bayesian network and performing Bayesian inference. Then, it outputs the bid price by means of a bandit algorithm and online optimization. This approach enables online optimization that considers uncertainty from the limited information available to advertisers. We conducted simulations using real data and confirmed the effectiveness of the proposed method for both open-source data and data provided by negocia, Inc., which provides an automated Internet advertising management system.

show abstract

A Unified Solution to Constrained Bidding in Online Display Advertising

Cited by 29 publications

References 16 publications

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning

An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions

Keyword-Level Bayesian Online Bid Optimization for Sponsored Search Advertising

Contact Info

Product

Resources

About