回复: 9
收起左侧

分享下亚马逊Advertisting 部门的Tech Bar

   
匿名用户-Z29PF  2021-3-14 16:25:48
本楼:   👍  7
100%
0%
0   👎

2021(1-3月) 分析|数据科学类 硕士 全职@amazon - Other - 其他  | Other | 在职跳槽

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
上周和亚马逊Advertisting 的同事聊了一下,她很热心的分享了他们招人的tech bar, 包括Marketing Science 和 Data Science 两部分。这个list 很全面,但面试的时候只是选几个自己的强项考核。希望对大家有帮助,求大米:). .и

. 1point 3acres
1. Marketing Science Methodologies
a) Basics of Descriptive Analytics:
i. Measures of central tendency (mean, median, mode).google  и
ii. Measures of spread (range, standard deviation)
iii. Quantiles and inter-quantile distance
b) Basics of Probability:. .и
i. Calculate probability of union and intersection of multiple of events
ii. Ability to use Bayes Theorem
iii. Know the difference between independent and un-correlated random variables
iv. Simple combinatorics, e.g., probability of 4 aces in deck of cards
c) Basic Probability Distributions:
i. What is a probability distribution function? (Univariate)
ii. Understanding differences between basic continuous distributions (e.g. uniform, normal, exponential: memoryless property).
iii. Understanding basic discrete distributions (e.g. Bernoulli or coin toss)
iv. What is mean/variance?. 1point3acres.com
d) Basics of Estimation and Hypothesis Testing:
i. Recognize difference between population parameters versus sample statistic. 1point3acres
ii. Ideas behind simple Hypothesis Testing and its relation to Confidence Intervals
iii. Type 1 error, Type II error
iv. P-values, statistical significance.google  и
v. Basics of A/B testing.
e) Basics of Regression:
i. Concepts, and terminology
ii. Simple linear regression model, assumptions, Ordinary Least Squares (OLS)
f) Basics of Forecasting:
iii. Moving Averages
iv. Serial correlation and seasonality ..

2. Data Science Disciplines
. Χ
a) Data Analysis:
i. Best practices for displaying data
ii. Boxplots
iii. Scatterplots
iv. Contingency tables (2x2 tables)
v. Simpson’s paradox
vi. Regression to the mean-baidu 1point3acres
vii. Data manipulation questions (e.g., wide to long format conversions, creation of graphs that require non-trivial data manipulation)
viii. QQ-plots
ix. Histograms
x. Dimension reduction techniques (e.g., PCA)
b) Estimation and Hypothesis Testing:
i. Frequentist sampling concepts
ii. Simple random sample (SRS) definition
iii. Properties of estimators, bias and variance
iv. Power
v. Confidence interval interpretation
vi. Multiple testing issues (familywise error, Bonferroni, FDR)
vii. One-sample versus two-sample hypothesis testing, paired versus unpaired data tests
viii. Test for proportions versus tests for population mean (tweak).google  и
ix. Chi-squared tests for contingency tables
x. Basics of maximum likelihood estimation
xi. Basic bootstrap methods to obtain confidence intervals (e.g., percentile method)
xii. Tests for equal variance
xiii. ANOVA concepts
xiv. Likelihood ratio test
c) Regression:
i. The concept of Best Linear Unbiased Estimator (BLUE)
ii. Statistical properties of least squares estimates (model assumptions). 1point 3acres
iii. Residual analysis (error term diagnostics)
iv. Confidence intervals vs prediction intervals
v. Data transformations (log, square root, Box-Cox). 1point 3acres
vi. Multiple linear regression model; interpretation of multiple regression coefficients
.--vii. Interaction effects (mechanics and interpretation). Χ
viii. Regression diagnostics. Χ
ix. Multicollinearity
x. Hypothesis tests in regression modeling
xi. Stepwise variable selection methods and their associated problems
xii. Logistic regression
xiii. Weighted least squares
xiv. Regression methods for repeated measures or longitudinal data (fixed effects versus random effects models)
xv. Fixed effects estimator
xvi. Random effects estimator along with Shrinkage concepts
d) Experiments:
i. Knowledge of different types of bias (selection, nonresponse, misreporting)
ii. Correlation vs causation
iii. Benefits of randomization
iv. Multiple testing issues
e) Basic Machine Learning:
i. Supervised vs unsupervised learning
ii. Bias-variance tradeoff
iii. Cross-validation. From 1point 3acres bbs
iv. Use of logistic regression for classification problems
v. Confusion matrix, precision, recall, F1 score, AUC
vi. Basics of text data mining (bag-of-words data structure)
vii. Boosting
viii. Decision Trees, Random forest (bagging)
ix. Regularization methods
x. K-means (k-medians); Distance Measures. 1point3acres.com
xi. Support vector machines
xii. Convexity
xiii. K-nearest neighbors
xiv. Different loss functions
f) Causal Inference:
i. Randomized control trials
ii. What is a treatment effect? SATE, SATT, SATC, selection problem
iii. What is endogeneity and
您好!
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
使用VIP即刻解锁阅读权限或查看其他获取积分的方式
游客,您好!
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
VIP即刻解锁阅读权限查看其他获取积分的方式
ching
ii. Look-alike modelling
iii. Programmatic advertising
iv. Search engine optimization methods
h) Market Structure:. ----
i. Types of Market Structure (e.g. Perfect competition, Monopoly, Oligopoly, Monopolistic competition, Contestable markets)-baidu 1point3acres
ii. Market Concentration Measures (e.g. N-firm concentration ratio, Herfindahl-Hirschman Index)
iii. Market Analysis Dimensions (e.g. Market size, Market trends, Market growth rate, Market profitability, Industry cost structure, Distribution channels)
iv. Market Research Techniques (e.g. Secondary Data Sources, Unstructured Research, Surveys)
i) Online Content:
i. User-generated or professional content: natural language processing (volume, sentiment and topic analysis)
ii. Representativeness of online content (e.g. customer reviews): self-selection, extremes bias, J-shaped star ratings
iii. Influence on brand reputation plus as input to media planning
j) Product launch:
i. Product innovation, quality improvements and differences in customer vs manufacturer perception of these terms
ii. New product diffusion at aggregate (diffusion model) and audience segmentation level (innovators, early adopters…)
iii. Drivers of successful new product launch: roles of customer information, perceived risk, product price and advertising. .и


评分

参与人数 21大米 +26 收起 理由
torontotina + 1 很有用的信息!
hikagu + 1 很有用的信息!
百米飞人张宝华 + 2 很有用的信息!
galabananana + 1 很有用的信息!
lajiaomian + 2 很有用的信息!

查看全部评分


上一篇:fb ds 新鲜面经
下一篇:求问compass product analyst面经

本帖被以下淘专辑推荐:

leeshuang0821 2021-3-19 12:21:30 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   16
100%
0%
0
请问楼主这个适用于ads下面的BIE吗?
回复

使用道具 举报

hwaaron 2021-3-19 13:40:16 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   224
93%
7%
18
谢谢分享, 真棒!
回复

使用道具 举报

TinaS 2021-3-25 08:31:35 | 显示全部楼层
本楼:    0
0%
0%
0  
全局:   15
100%
0%
0
zan!
回复

使用道具 举报

felicity11 2021-3-25 09:42:32 来自APP | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   173
98%
2%
3
leeshuang0821 发表于 2021-03-18 21:21:30
请问楼主这个适用于ads下面的BIE吗?
BIE 应该不是这个要求,我对热带雨林BIE的理解是更多datamart tables, Tableau dashboard,或各种reports 搭建,建模或分析会比较少。
回复

使用道具 举报

yz9 2021-3-25 11:20:41 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   814
65%
35%
431
艹这个真的是统计phd level了,很多都是比较热门的研究方向
回复

使用道具 举报

RRgogo 2021-3-25 11:21:14 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   456
98%
2%
11
看到这个list我只想说,data方面的面试范围是真的广!
回复

使用道具 举报

Mag2679 2021-3-25 13:36:29 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   1257
91%
9%
126
请问是否适用于Data engineer的岗位呢?谢谢~
回复

使用道具 举报

jumpjump66 2021-3-25 15:57:31 | 显示全部楼层
本楼:   👍  0
0%
0%
0   👎
全局:   16
100%
0%
0
赞楼主!! 很有用的信息!
回复

使用道具 举报

地里匿名用户
匿名用户-NSWEV  2021-4-8 22:05:57 来自APP
本楼:   👍  0
0%
0%
0   👎
面的l5,面完反馈可能会被降级,还有l4的hc吗
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 注册账号
隐私提醒:
  • ☑ 禁止发布广告,拉群,贴个人联系方式:找人请去🔗同学同事飞友,拉群请去🔗拉群结伴,广告请去🔗跳蚤市场,和 🔗租房广告|找室友
  • ☑ 论坛内容在发帖 30 分钟内可以编辑,过后则不能删帖。为防止被骚扰甚至人肉,不要公开留微信等联系方式,如有需求请以论坛私信方式发送。
  • ☑ 干货版块可免费使用 🔗超级匿名:面经(美国面经、中国面经、数科面经、PM面经),抖包袱(美国、中国)和录取汇报、定位选校版
  • ☑ 查阅全站 🔗各种匿名方法

本版积分规则

Advertisement
>
快速回复 返回顶部 返回列表