论文标题：Analyzing and predicting the spatial penetration of Airbnb in U.S. cities

期刊：EPJ Data Science

作者：Giovanni Quattrone, Andrew Greatorex, Daniele Quercia, Licia Capra and Mirco Musolesi

发表时间：2018/09/19

数字识别码：10.1140/epjds/s13688-018-0156-6

原文链接：https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-018-0156-6?utm_source=WeChat&utm_medium=Website_linksSocial_media_organic&utm_content=CelZha-MixedBrand-multijournal-Multidisciplinary-China&utm_campaign=ORG_AWA_CZH_BMCWechat_dailyposts_blogs

微信链接：https://mp.weixin.qq.com/s/YcRRf3-ikaaG5EZEgN0sCg

最近发表在EPJ Data Science上的研究表明，Airbnb（指民宿预约平台“爱彼迎”，也代指该平台上的民宿）在不同城市中的分布可能遵循相同的模式，决定其位置的几个因素中包括该地区在创意行业中工作的居民的数量。

图片来源：Pixabay.com/Foundry

来自英国米德尔塞克斯大学的通讯作者Giovanni Quattrone博士说：“以前Airbnb的经济模型过分强调了与市中心距离远近的重要性。但是我们发现其他因素可能也同样重要，比如附近有受过教育的创意工作者，我们称之为波西米亚主义者，有些学者会把他们称为‘创意阶级’。”

研究者在美国的8个城市中调查了Airbnb出租房的分布情况与附近地理、社会和经济状况的关系，这8个城市分别是奥斯汀、洛杉矶、曼哈顿、新奥尔良、奥克兰、圣地亚哥、旧金山和西雅图。

作者们发现的这个Airbnb分布规律使他们可以建立一个预测模型，用于未来预测Airbnb在另一座城市可能的分布情况。这个预测模型的验证便是通过对比这8个城市Airbnb分布的预测情况和实际情况完成的，结果显示模型对这8个城市的预测精确度很高。这个模型可能对Airbnb的监管机构很有用，让监管机构可以制定政策防止同一片区域有过多的短租房，同时让那些从住客增长中可以获得经济收益的区域发展出更多的Airbnb。

Quattrone博士说：“本研究的重要发现之一是我们在美国8个城市中调查得到的结果惊人相似。我们特意选择了这几座城市，是因为它们在规模、人口组成、富裕程度和生活成本上有很大差异。鉴于这些差异以及我们观察到的高度一致的模式表明，某种程度上而言我们的模型可以应用于之前没有被分析过的城市，预测这座城市中Airbnb的扩散并提出Airbnb分布情况的原因。”

研究者们为了搭建模型，下载了每个地区所有Airbnb的列表，测算了它们距离市中心的距离，衡量了包括交通路线、平均家庭收入、在创意行业工作的居民以及到公共景点的距离在内的地理和社会经济因素。

作者提醒，虽然这8座城市代表了多种社会经济情况，但它们都是美国城市，因此这些结果可能无法推广到其他国家的城市。

摘要：In the hospitality industry, the room and apartment sharing platform of Airbnb has been accused of unfair competition. Detractors have pointed out the chronic lack of proper legislation. Unfortunately, there is little quantitative evidence about Airbnb’s spatial penetration upon which to base such a legislation. In this study, we analyze Airbnb’s spatial distribution in eight U.S. urban areas, in relation to both geographic, socio-demographic, and economic information. We find that, despite being very different in terms of population composition, size, and wealth, all eight cities exhibit the same pattern: that is, areas of high Airbnb presence are those occupied by the “talented and creative” classes, and those that are close to city centers. This result is consistent so much so that the accuracy of predicting Airbnb’s spatial penetration is as high as 0.725.

阅读论文全文请访问：https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-018-0156-6?utm_source=WeChat&utm_medium=Website_linksSocial_media_organic&utm_content=CelZha-MixedBrand-multijournal-Multidisciplinary-China&utm_campaign=ORG_AWA_CZH_BMCWechat_dailyposts_blogs

期刊介绍：EPJ Data Science (https://epjdatascience.springeropen.com/) covers a broad range of research areas and applications and particularly encourages contributions from techno-socio-economic systems, where it comprises those research lines that now regard the digital “tracks” of human beings as first-order objects for scientific investigation. Topics include, but are not limited to, human behavior, social interaction (including animal societies), economic and financial systems, management and business networks, socio-technical infrastructure, health and environmental systems, the science of science, as well as general risk and crisis scenario forecasting up to and including policy advice.

2017 Journal Metrics

Citation Impact

2.982 - 2-year Impact Factor

3.042 - 5-year Impact Factor

1.361 - Source Normalized Impact per Paper (SNIP)

0.943 - SCImago Journal Rank (SJR)

（来源：科学网）