注册一亩三分地论坛,查看更多干货!
您需要 登录 才可以下载或查看附件。没有帐号?注册账号
x
本帖最后由 匿名 于 2020-1-17 01:18 编辑
senior manager和director一起面的,问的大部分是地里的面经题。发个面经回报地里攒攒人品。
- 100 obs, 100 features 如何处理high-dimensional problem
- 有另一个dataset, 1000 obs, 100个同样的features, but predicted response for another kind of enginee, 问whether you can borrow information from the larger dataset to help predict response for the ori-technical people?
- You're given some observational data, plot y against x1, find no pattern but the client expects x1 to be important for y, why this occurs and what would you do?
. From 1point 3acres bbs.1point3acres
|