1.Perform Standard Normalization
2.Handwrite a Decision Tree Generation Process
3.Probability of Blue Wrapper Candy
4.Movie Collection Scoring Function
5.Coding Exercise
6.In-depth Machine Learning Discussion
7.General Machine Learning Knowledge
8.Panel Exercise Presentation
9.Why is penalization necessary and how is it implemented in neural networks?
10.What is a ROC curve, and can you explain sensitivity and specificity?
11.Discuss your favorite machine learning model.
12.Explain the difference between supervised and unsupervised learning.
13.Handling Multiple Testing at Netflix
14.Designing an A/B Test for Netflix
15.Balancing Covariates in Research
16.Estimating Spill-over Effect in Research
17.Handling Specific Video Processing Tasks
18.Panel Interview and Hiring Manager Questions
19.Advanced Machine Learning Concepts
20.Basic Machine Learning Concepts
21.Machine Learning Fundamentals
22.Classifier Metric Selection for Stock Performance Detection
23.Gradient Calculation
24.Use of Dropout in Neural Networks
25.Clustering standard error
26.Conducting a placebo test
27.Using diff-in-diff to estimate a national level policy shock
28.Explain the concept of diff-in-diff
29.Details of Propensity Score in Observational Causal Inference
30.Metrics and Sample Size Determination for A/B Testing to Improve Sign Up Rate
1. Perform Standard Normalization
Perform standard normalization on a given dataset. The task can be completed using a library function.
2. Handwrite a Decision Tree Generation Process
Given a set of data, handwrite the decision tree generation process, focusing on the branching process using the Gini index.
3. Probability of Blue Wrapper Candy
Given the data on how many candies of each color each friend got, what is the probability of receiving a candy with a blue colored wrapper if your last name is Silver?
4. Movie Collection Scoring Function
Implement a function that takes as input a ranked list of movies, a list of movie collections, and a value of k. The function should return the index of the highest scored collection based on the top k movies in each collection using the formula: score = sum(1/rank) for the top k movies.
5. Coding Exercise
Implement a simple model on a notebook, similar to a document clustering feature.
解锁更多真题，请点此 登录 篱笆帮
高频题（0）
