CIA-Towards a Unified Marketing Optimization Framework for e-Commerce Sponsored Search.

As the largest e-commerce platform, Taobao helps advertisers reach billions of search requests each day with its sponsored search service, which has also contributed considerable revenue to the platform. How to design a suit of marketing optimization tool to cater various advertiser demands while balancing platform revenue and consumer experience is significant to a healthy and sustainable marketing ecosystem, among which bidding strategy plays a critical role. Traditional keyword-level bidding optimization only provides a coarse-grained match between advertisement and impression. Meanwhile impression-level expected value bidder is not applicable to various demand optimization of massive advertisers, not to mention its lack of mechanism to balance benefits of three parties. In this paper we propose emph{Customer Intelligent Agent}, a bidding optimization framework which designs an impression-level bidding strategy to reflect advertiseru0027s conversion willingness and budget control. In this way, with a simplified control ability for advertisers, CIA is capable of fulfilling various e-commerce advertiser demands in different levels, such as GMV optimization, style comparison etc. Additionally, a replay based simulation system is designed to predict the performance of different take-rate. CIA unifies the benefits of three parties in the marketing ecosystem without changing the classic expected Cost Per Mille mechanism. Our extensive offline simulations and large-scale online experiments on emph{Taobao Search Advertising} platform verify the high effectiveness of the CIA framework. Moreover, CIA has been deployed online as a major bidding tool for advertisers in TSA.