Although the bandits framework is a classical and well-suited approach for
optimal bidding strategies in sponsored search auctions, industrial attempts
are rarely documented. This paper outlines the development process at Zalando,
a leading fashion e-commerce company, and describes the promising outcomes of a
bandits-based approach to increase profitability in sponsored search auctions.
We discuss in detail the technical and theoretical challenges that were
overcome during the implementation, as well as the mechanisms that led to
increased profitability.

本文记录了时尚电商巨头 Zalando 基于 Bandits 框架的拍卖策略的开发过程及实施过程中的技术和理论挑战，并描述了该策略带来的盈利增长。

学习最佳投标策略：电子商务广告案例研究

Learning Optimal Bidding Strategy: Case Study in E-Commerce Advertising

Sponsored search auctions constitute one of the most successful applications
of microeconomic mechanisms. In mechanism design, auctions are usually designed
to incentivize advertisers to bid their truthful valuations and to assure both
the advertisers and the auctioneer a non-negative utility. Nonetheless, in
sponsored search auctions, the click-through-rates (CTRs) of the advertisers
are often unknown to the auctioneer and thus standard truthful mechanisms
cannot be directly applied and must be paired with an effective learning
algorithm for the estimation of the CTRs. This introduces the critical problem
of designing a learning mechanism able to estimate the CTRs at the same time as
implementing a truthful mechanism with a revenue loss as small as possible
compared to an optimal mechanism designed with the true CTRs. Previous work
showed that, when dominant-strategy truthfulness is adopted, in single-slot
auctions the problem can be solved using suitable exploration-exploitation
mechanisms able to achieve a per-step regret (over the auctioneer's revenue) of
order $O(T^{-1/3})$ (where T is the number of times the auction is repeated).
It is also known that, when truthfulness in expectation is adopted, a per-step
regret (over the social welfare) of order $O(T^{-1/2})$ can be obtained. In
this paper we extend the results known in the literature to the case of
multi-slot auctions. In this case, a model of the user is needed to
characterize how the advertisers' valuations change over the slots. We adopt
the cascade model that is the most famous model in the literature for sponsored
search auctions. We prove a number of novel upper bounds and lower bounds both
on the auctioneer's revenue loss and social welfare w.r.t. to the VCG auction
and we report numerical simulations investigating the accuracy of the bounds in
predicting the dependency of the regret on the auction parameters.

该论文扩展了有关单 Slot 拍卖中的 sponsored search auctions 的机制设计的研究，并研究了使用级联模型来解决多 Slot 拍卖中的 CTR 估计和真实机制设计的问题。

多广告位赞助搜索竞拍的真实学习机制及外部性

Truthful Learning Mechanisms for Multi-Slot Sponsored Search Auctions  with Externalities

We consider the budget optimization problem faced by an advertiser
participating in repeated sponsored search auctions, seeking to maximize the
number of clicks attained under that budget. We cast the budget optimization
problem as a Markov Decision Process (MDP) with censored observations, and
propose a learning algorithm based on the wellknown Kaplan-Meier or
product-limit estimator. We validate the performance of this algorithm by
comparing it to several others on a large set of search auction data from
Microsoft adCenter, demonstrating fast convergence to optimal performance.

本研究考虑广告主在参加重复竞价搜索拍卖时所面临的预算优化问题，将其作为带有被审查观测的马尔可夫决策过程（MDP）来建模，并提出基于 Kaplan-Meier 或产物极限估计器的学习算法。在微软广告中心的大量搜索竞拍数据上，将此算法与几种其他算法进行比较，证明其快速收敛的最佳性能。