acrehr的理财空间

自一个在米国读商科的前L'oreal marketing MT。觉得很好玩，mraketing到底是什么？data based marketing在多数企业的实际运营中到底有何种的现实意义？我想至少在中国，这还是一条漫长的路:p

引用

What SAS and Excel could do
The interesting graph from a SAS book.
At some time you will probably want to create your own custom formats - especially if you use a lot of coded data. Imagine that you have just completed a survey for your company and to save disk space and time, all the responses to the survey questions are coded. For example, the age categories teen, adult, and senior are coded as numbers 1, 2 and 3. This is convenient for data entry and analysis but bothersome when it comes time to interpret the results. You could present your result along with a code book, and your company directors could look up the codes as they read the results. But this will probably not get you that promotion you have been looking for. A better solution is to create user-defined formats using PROC FORMAT.
回忆从前在公司里做的事，对比现在的practice，有很多有趣的联系。
- Database Modeling的final project是一个business cycle analysis。老师很好心的做了一些pivot tables让我们熟悉数据。第一次开会时我和Srivydia相视而笑，太熟悉了这个格式。
"It reminds me of those SAP data I pulled down from company database..."
"I know!!" She said.
- 前面讲到的PROC FORMAT，中国大陆有哪个corporate能先锋到marketing会用SAS？就连我从前公司的research部门也是excel随便搞搞，直接甩给brand marketing巨大的slides，各种不着边际的bar chart pie chart。工作第一年时老板给我做一个national survey，第一次正式用coding来处理，其实不大的数据。present之前，煞有介事的做了个summary table解释各个参数的coding rule，自我感觉还非常好觉得自己哎，实在是太professional了。如今...按照SAS book的说法，看来从那时候起我就注定没有promotion了，哈哈。
- SAS还可以write simple custom reports, each record/observation on one page. Could be applied to individual customer reports, score card, customized invitation or newsletter. 我从前可都是辛辛苦苦的copy/paste啊...=.=
- Corporate环境下所有的forecasting/budgeting都是percentage-based，意味着一个估计比较准确的sales数据需要多方（marketing, logistics, finance）商讨若干久讨价还价align好各方的知识和感觉。风险最大时是哪一方在brand meeting里dominating了，那就完了，下个月/下个季度的sales就没谱到天上了。（往往是brand这边欺负logistics新新新新新来的吧）那时候logistics最得意了，掉头马上洪水般的邮件should have been, could have been倾倒给marketing，而且一定copy老板。现在出来这个局了，觉得这帮人都是傻缺，有没有意义啊，吵的是什么啊，你对你那个estimated 5%就那么有信心？你嘴硬个屁啊，有这点为脸面吵架的时间，早好收集完毕数据，做predictive modling了。
- Ed 说dataminer是个很受corporate欢迎的工种，虽然很被academics鄙视（已经被Ed折磨着读了无数的关于regression pros and cons的学术文献...）。想来大概也是老板们也看不下去了。统一标准呗。虽然我们自称dataminer的自己也很心虚，你feed什么进去才最关键 - 可那个是你一个小p孩能manage的吗？Domain knowledge啊... Anyway，还是比吵来吵去好。

百度搜索:Excel
Google搜索:Excel
雅虎搜索:Excel
SOSO搜索:Excel