Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOptimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising
83
0
0.0
(
0
)
Added by
Xiangyu Liu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue. However, most of the state-of-the-art auction mechanisms only focus on optimizing a single performance metric, e.g., either social welfare or revenue, and are not suitable for e-commerce advertising with various, dynamic, difficult to estimate, and even conflicting performance metrics. In this paper, we propose a new mechanism called Deep GSP auction, which leverages deep learning to design new rank score functions within the celebrated GSP auction framework. These new rank score functions are implemented via deep neural network models under the constraints of monotone allocation and smooth transition. The requirement of monotone allocation ensures Deep GSP auction nice game theoretical properties, while the requirement of smooth transition guarantees the advertiser utilities would not fluctuate too much when the auction mechanism switches among candidate mechanisms to achieve different optimization objectives. We deployed the proposed mechanisms in a leading e-commerce ad platform and conducted comprehensive experimental evaluations with both offline simulations and online A/B tests. The results demonstrated the effectiveness of the Deep GSP auction compared to the state-of-the-art auction mechanisms.
rate research
Read More
In e-commerce advertising, it is crucial to jointly consider various performance metrics, e.g., user experience, advertiser utility, and platform revenue. Traditional auction mechanisms, such as GSP and VCG auctions, can be suboptimal due to their fixed allocation rules to optimize a single performance metric (e.g., revenue or social welfare). Recently, data-driven auctions, learned directly from auction outcomes to optimize multiple performance metrics, have attracted increasing research interests. However, the procedure of auction mechanisms involves various discrete calculation operations, making it challenging to be compatible with continuous optimization pipelines in machine learning. In this paper, we design underline{D}eep underline{N}eural underline{A}uctions (DNAs) to enable end-to-end auction learning by proposing a differentiable model to relax the discrete sorting operation, a key component in auctions. We optimize the performance metrics by developing deep models to efficiently extract contexts from auctions, providing rich features for auction design. We further integrate the game theoretical conditions within the model design, to guarantee the stability of the auctions. DNAs have been successfully deployed in the e-commerce advertising system at Taobao. Experimental evaluation results on both large-scale data set as well as online A/B test demonstrated that DNAs significantly outperformed other mechanisms widely adopted in industry.
Standard ad auction formats do not immediately extend to settings where multiple size configurations and layouts are available to advertisers. In these settings, the sale of web advertising space increasingly resembles a combinatorial auction with complementarities, where truthful auctions such as the Vickrey-Clarke-Groves (VCG) can yield unacceptably low revenue. We therefore study core selecting auctions, which boost revenue by setting payments so that no group of agents, including the auctioneer, can jointly improve their utilities by switching to a different outcome. Our main result is a combinatorial algorithm that finds an approximate bidder optimal core point with almost linear number of calls to the welfare maximization oracle. Our algorithm is faster than previously-proposed heuristics in the literature and has theoretical guarantees. We conclude that core pricing is implementable even for very time sensitive practical use cases such as realtime auctions for online advertising and can yield more revenue. We justify this claim experimentally using the Microsoft Bing Ad Auction data, through which we show our core pricing algorithm generates almost 26% more revenue than VCG on average, about 9% more revenue than other core pricing rules known in the literature, and almost matches the revenue of the standard Generalized Second Price (GSP) auction.
Advertising creatives are ubiquitous in E-commerce advertisements and aesthetic creatives may improve the click-through rate (CTR) of the products. Nowadays smart advertisement platforms provide the function of compositing creatives based on source materials provided by advertisers. Since a great number of creatives can be generated, it is difficult to accurately predict their CTR given a limited amount of feedback. Factorization machine (FM), which models inner product interaction between features, can be applied for the CTR prediction of creatives. However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback. To address these two issues, we propose an Automated Creative Optimization (AutoCO) framework to model complex interaction between creative elements and to balance between exploration and exploitation. Specifically, motivated by AutoML, we propose one-shot search algorithms for searching effective interaction functions between elements. We then develop stochastic variational inference to estimate the posterior distribution of parameters based on the reparameterization trick, and apply Thompson Sampling for efficiently exploring potentially better creatives. We evaluate the proposed method with both a synthetic dataset and two public datasets. The experimental results show our method can outperform competing baselines with respect to cumulative regret. The online A/B test shows our method leads to a 7 increase in CTR compared to the baseline.
Showing items that do not match search query intent degrades customer experience in e-commerce. These mismatches result from counterfactual biases of the ranking algorithms toward noisy behavioral signals such as clicks and purchases in the search logs. Mitigating the problem requires a large labeled dataset, which is expensive and time-consuming to obtain. In this paper, we develop a deep, end-to-end model that learns to effectively classify mismatches and to generate hard mismatched examples to improve the classifier. We train the model end-to-end by introducing a latent variable into the cross-entropy loss that alternates between using the real and generated samples. This not only makes the classifier more robust but also boosts the overall ranking performance. Our model achieves a relative gain compared to baselines by over 26% in F-score, and over 17% in Area Under PR curve. On live search traffic, our model gains significant improvement in multiple countries.
Modern e-commerce catalogs contain millions of references, associated with textual and visual information that is of paramount importance for the products to be found via search or browsing. Of particular significance is the book category, where the author name(s) field poses a significant challenge. Indeed, books written by a given author (such as F. Scott Fitzgerald) might be listed with different authors names in a catalog due to abbreviations and spelling variants and mistakes, among others. To solve this problem at scale, we design a composite system involving open data sources for books as well as machine learning components leveraging deep learning-based techniques for natural language processing. In particular, we use Siamese neural networks for an approximate match with known author names, and direct correction of the provided authors name using sequence-to-sequence learning with neural networks. We evaluate this approach on product data from the e-commerce website Rakuten France, and find that the top proposal of the system is the normalized author name with 72% accuracy.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
