[스크랩]How To Crack Spotify Data Science Technical Screen Interview

How To Crack Spotify Data Science Technical Screen Interview
List of exact Python/SQL commands and experimentation topics you should know to nail Spotify Tech Screen

Image Source: @felipepelaquim
If you are preparing for Technical Screen or Technical Interview at Spotify then most likely you are looking for answers to the following questions:
How can I start preparing for Spotify Data Science tech interview?
What can I expect from Spotify Data Science tech interview?
This article will cover the following topics:
- Tech Screen Duration
- Part 1: Python Question
- Part 2: SQL Question
- Part 3: A/B Testing Question
Tech Screen Duration
This technical interview takes about 45 minutes and is divided into three parts: Python, SQL, and Experimentation.

Image Source: cottonbro
Part 1: Python Question
The first tech screen question is usually a data wrangling or data transformation question which you should do in Python, although you can do it in SQL too. This question aims to find out whether you can make use of some basic concepts such as filtering and aggregation in Python. Whether you can make use of the two most popular libraries: Pandas and NumPy.
Example Question
How to fix a bug in the data where a specific device’s data is halved for some reason?
Learn the basic functionalities in Pandas such as grouping, summing, averaging, filtering (with single and multiple values) such as:
df.groupby(“x”)
df.groupby(“x”)[“y”].sum()
df.groupby(“x”)[“y”].avg()
df[df[“x”] == k]
df[df.x.isin([k,l])]

Learn the basic filtering function in Numpy:
df[“new_vb”] = np.where(condition, value if condition true, value if condition false)

Part 2: SQL Question
The second question on the tech screen is a coding question in SQL where you need to know the basic SQL functions to filter the data, to perform joins between the two data while knowing the concept of A/B testing in depth.
To solve this problem you will need to be familiar with the basic concepts behind A/B testing such as control vs experimental groups, selecting primary success or performance metrics, and calculating it per each of these two groups. Everything you need to know about A/B testing to solve this problem can be found here: https://towardsdatascience.com/simple-and-complet-guide-to-a-b-testing-c34154d0ce5a
Simple and Complete Guide to A/B Testing
End-to-end A/B testing for your Data Science experiments for non-technical and technical specialists with examples and…
towardsdatascience.com

To solve this problem learn the following basic functions in SQL:
SELECT
COUNT
AVG
LEFT JOIN, RIGHT JOIN
WHERE
GROUP BY
HAVING
ORDER BY
LIMIT
You should be able to calculate metrics such as average screen time per control and experimental group where user information is in one table and screen time is in another. This means you should be able to join two tables and also keep the data only for the users who partipated in the A/B test (LEFT JOIN or RIGHT JOIN) depending on your choice of table ordering.
For example:

One thing you want to keep in mind is that you only need the usage data of the A/B test users after the A/B test started for them.
Part 3: A/B Testing Question
The third and final section of the interview is about A/B testing. These are static questions that you can find in every single experimentation-related interview such as:
p-values
statistical significance
hypothesis-testing
t-test vs z-test
confidence interval
Type I and Type II error
and more
Study the following 2 blog posts that contain everything basic statistical concepts such as p-values etc and about A/B testing, then you will be able to answer all the questions asked during this last part of the tech screen.
Fundamentals Of Statistics For Data Scientists and Data Analysts
Key statistical concepts for your data science or data analytics journey
towardsdatascience.com

Simple and Complete Guide to A/B Testing
End-to-end A/B testing for your Data Science experiments for non-technical and technical specialists with examples and…
towardsdatascience.com


Image Source: cottonbro
Disclaimer: you can find more information about the type of questions to expect during Spotify or any other company’s interview questions on the websites such as Glassdoor.com.
If you liked this article, here are some other articles you may enjoy:
Understanding Bias-Variance Trade-Off, Overfitting and Regularization in Machine Learning
Introduction to bias-variance trade-off, overfitting & how to solve overfitting using regularization: Ridge and Lasso…
towardsdatascience.com

Data Sampling Methods in Python
A ready-to-run code with different data sampling techniques to create a random sample in Python
tatev-aslanyan.medium.com

PySpark Cheat Sheet: Big Data Analytics
Here is a cheat sheet for the essential PySpark commands and functions. Start your big data analysis in PySpark.
medium.com

Bias-Variance Trade-off in Machine Learning
Introduction to bias-variance trade-off in Machine Learning and Statistical models
tatev-aslanyan.medium.com

Monte Carlo Simulation and Variants with Python
Your Guide to Monte Carlo Simulation and Must Know Statistical Sampling Techniques With Python Implementation
towardsdatascience.com

Predicting Bitcoin’s Price With Recurrent Neural Networks
Who hasn’t heard about the most famous digital money in the world, the cryptocurrency of decade? That’s right, I am…
levelup.gitconnected.com

Thanks for the read
I encourage you to join Medium to have complete access to all my articles about Data Science, Machine Learning, AI, and other topics.
Follow me up on Medium to read more articles about various Data Science and Data Analytics topics. For more hands-on applications of Machine Learning, Mathematical and Statistical concepts check out my Github account.
I welcome feedback and can be reached on LinkedIn.
Happy learning!
157

https://unsplash.com/photos/Q1p7bh3SHj8