Randomized Experimental Design via Geographic Clustering

Randomized Experimental Design via Geographic Clustering
复制标题

通过地理聚类的随机实验设计

DOI:
10.1145/3292500.3330778
复制
发表时间:
2019
期刊:
ACM
影响因子:
--
通讯作者:
Najmi, Amir
Najmi, Amir
中科院分区:
--
文献类型:
--
作者:
Rolnick, David;Aydin, Kevin;Pouget-Abadie, Jean;Kamali, Shahab;Mirrokni, Vahab;Najmi, Amir

文献摘要

参考文献

被引文献

相似文献

基于web的服务经常运行随机实验来改进它们的产品。运行这些实验的一种流行方法是使用地理区域作为实验单元,因为这不需要跟踪单个用户或浏览器cookie。由于用户可能从多个地理位置发出查询,因此不能认为地理区域是独立的,并且在实验中可能存在干扰。在本文中,我们研究了这一问题,并首先提出了一种新的geoocuts算法,该算法通过形成地理簇来最小化干扰,同时保持簇大小的平衡。我们使用来自谷歌Search的随机匿名流量样本来形成一个表示用户运动的图,然后构建该图的地理连贯聚类。我们的主要技术贡献是一个统计框架来衡量聚类的有效性。此外,我们进行了实证评估,表明GeoCUTS的性能与手工制作的地理区域相比,无论是新的还是现有的指标。
Web-based services often run randomized experiments to improve their products. A popular way to run these experiments is to use geographical regions as units of experimentation, since this does not require tracking of individual users or browser cookies. Since users may issue queries from multiple geographical locations, geo-regions cannot be considered independent and interference may be present in the experiment. In this paper, we study this problem, and first present GeoCUTS, a novel algorithm that forms geographical clusters to minimize interference while preserving balance in cluster size. We use a random sample of anonymized traffic from Google Search to form a graph representing user movements, then construct a geographically coherent clustering of the graph. Our main technical contribution is a statistical framework to measure the effectiveness of clusterings. Furthermore, we perform empirical evaluations showing that the performance of GeoCUTS is comparable to hand-crafted geo-regions with respect to both novel and existing metrics.
DOI: --
发表时间: 2002-09
期刊: --
影响因子: --
作者:
Xiaojin Zhu;Zoubin Ghahramani
通讯作者: Xiaojin Zhu;Zoubin Ghahramani
DOI: 10.2139/ssrn.2477076
发表时间: 2014
影响因子: 20.6
作者:
Dylan Walker;Lev Muchnik
通讯作者: Lev Muchnik
DOI: 10.1515/jci-2015-0021
发表时间: 2017-03-01
影响因子: 1.4
作者:
Eckles, Dean;Karrer, Brian;Ugander, Johan
通讯作者: Ugander, Johan
DOI: 10.1111/biom.12615
发表时间: 2016-12
期刊: Biometrics
影响因子: 1.9
作者:
B. Shepherd;Ryan T. Jarrett;L. Fu
通讯作者: B. Shepherd;Ryan T. Jarrett;L. Fu
DOI: 10.1111/insr.12170
发表时间: 2016-04
影响因子: 2
作者:
C. Blumberg
通讯作者: C. Blumberg