搜索竞价中关键字最优化策略研究

项目名称： 搜索竞价中关键字最优化策略研究

项目编号： No.71272236

项目类型： 面上项目

立项/批准年度： 2013

项目学科： 管理科学

项目作者： 杨彦武

作者单位： 华中科技大学

项目金额： 54万元

中文摘要： 关键字是搜索竞价中联结广告主、搜索用户和搜索引擎之间的重要纽带。关键字的生成、选择与分组等过程都是搜索竞价广告主面临的核心决策问题，而且贯穿于搜索竞价活动的整个生命周期。本项目综合运用概率图、随机规划、随机集、自适应动态规划和优化控制等理论与方法，系统地研究针对搜索竞价推广活动整个生命周期的多层次关键字策略优化框架模型，分别从关键字的生成、扩展、定位、选择与组合以及动态调整几个方面研究最优化策略，并建立关键字策略实验环境对相关优化策略进行模拟验证，进而利用推广历史日志数据和正在实施的推广活动对关键字优化模型及其算法进行实际验证与评估，以确保本项目研究成果的实践价值。本项目的研究成果不仅能够在很大程度上提高我国搜索竞价广告与营销领域的理论研究水平，也能够为广大中小企业节省推广时间和广告费用的同时提高搜索竞价推广活动的效率，有效地促进搜索竞价推广与营销产业的发展，具有重要的科学意义和应用价值。

中文关键词： 电子商务；搜索竞价；策略优化；关键字优化；广告策略

英文摘要： In search auctions, keyword is a kernel bridge between advertisers, search users and search engines. Advertisers have to face a series of primary keyword-related decisions (e.g., keyword generation, selection and portfolio) throughout the entire lifecycle of search advertising campaigns. This project aims to systematically explore a hierarchical keyword optimization framework to support various keyword-related decisions during the entire lifecycle of search advertising campaigns, by utilizing probabilistic graphical model, stochastic programming, random sets theory, adaptive dynamic programming and optimal control theory. Based on this framework, we will develop optimal strategies for keyword generation, expansion, allocation, selection and portfolio with consideration of search advertising structures, and dynamical adjustment according to the realtime advertising performance. Furthermore, an experimental platform for keyword research optimization is built to encapsulate various settings of keyword-related decisions in search auctions. With field reports and logs from historical and ongoing search advertising campaigns, our keyword optimization framework and identified strategies are validated in order to ensure practical values of this research. The research achievements and findings of this project are both th

英文关键词： e-commerce；search auction；strategy optimization；keyword optimization；advertising strategy