FreeRange story - Google：经济预测专家可以让位了

FreeRange user yuebai li wanted you to see this:

"Google：经济预测专家可以让位了"

[2009.04.16] Googling the future Google 一下未来

Economic indicators 经济指标

Googling the future Google一下未来

Apr 16th 2009

From The Economist print edition

Internet search data may be useful for forecasters

网络搜索数据也许可以帮助经济预测专家

CLAIMS of clairvoyance, particularly when they come from economists, deserve a sceptical reception. Hal Varian, a professor of economics at the University of California, Berkeley who also happens to be Google’s chief economist, has no such pretensions, but he does believe that data on internet searches can help predict certain kinds of economic statistics before they become available.

人们具有预见能力的这一说，尤其是经济学家的预见能力通常都会引起质疑。加州大学伯克利分校的经济学教授，谷歌公司首席经济学家 Hal Varian 表示，他没有如此的洞察力和预见力，但他相信在某些经济统计数据公布之前，网络搜索的数据能够帮助预测这些数据。

In a new paper written with Hyunyoung Choi, a colleague at Google, he argues that fluctuations in the frequency with which people search for certain words or phrases online can improve the accuracy of the econometric models used to predict, for example, retail-sales figures or house sales. Actual numbers for such things are usually available only with a lag. But Google’s search data are updated every day, so they can in theory capture shifts in consumer behaviour before official numbers are released.

Varian 和谷歌的另一名同事 Hyunyoung Choi 最 新发表了一篇论文，他表示对于人们在网上搜索的一些字词短语，其频率的变化可以提高经济计量模型预测零售销售或售房数据的准确性。这些确切销售数据通常是 要滞后一段时间才能得到。但是谷歌搜索数据每天都在更新，因此理论上在官方数字出炉之前，们就把握住了消费者行为的变化。

These data are available through a site called Google Trends, which allows anyone who cares to do so to download an index of the aggregate volume of searches for particular terms or categories. Mr Varian and Mr Choi show that the addition of these search trends to econometric models improves the accuracy of their estimates.

人们可以在一个名叫谷歌趋势的网站上得到这些数据，并且可以下载特定条款或物品被搜索总量的指数。 Varian 和 Choi 表示，共同利用这些搜索趋势和经济计量模型就能够提高预测的准确性。

For example, using data on searches for trucks and SUVs to predict the monthly sales of motor vehicles reduces the average error by up to 18% compared with the predictions from a model that did not incorporate the search data. The volume of searches for Hong Kong carried out in countries like America, Britain, Australia and India also seems to predict eventual tourist arrivals to the territory from these countries rather well.

比如，与不用搜索数据的模型得出的预测相比，利用货车和 SUV 的搜索数据来预测汽车月销售量会减少高达 18% 的平均误差。在美国，英国，澳大利亚和印度等国进行的对香港的搜索似乎也能预测从这些国家到香港旅行的游客人数。

How widely could this idea be applied? For some things, like retail sales, the categories into which Google classifies its search-trend data correspond closely to what people may want to predict, such as the sales of a particular brand of car (see chart). For others, like sales of houses, things are less clear. It appears that searches for estate agents work better than those for home financing. But anything that makes the crystal ball less cloudy is welcome.

这 一方法的应用有多广？对于一些事物，比如零售销售，某些种类（谷歌将搜索趋势数据划分到该种类）和人们期望预测的事物非常相关，比如某一种汽车品牌的销 售。对于其它的项目，如房屋销售，情况就比较模糊。但对房地产经纪人的搜索似乎比对房屋抵押贷款机构的搜索更能清楚地说明房屋销售问题。无论如何，，只要 能使这个水晶球更加透明清晰，任何方法都是受人欢迎的。

随机文章：

鲜花销售:鲜花花束销售排行榜 2009-04-09

英国:对欧盟失去兴趣和影响 2007-11-15

日本 ：一党执政的危机 2007-09-27

服装：孟加拉追赶中国 2007-08-24

[2007.05.19]国际银行业:商潮 2007-05-30

收藏到：Del.icio.us

《城客》：第一本中文互动杂志！

经济学人

FreeRange WebReader - bringing the Internet to your mobile phone like never before!

Reading this on your Windows Smartphone, Palm or Blackberry? Try it now by clicking http://mwap.at

Posted via email from liyuebai's posterous