Sold to

mjs01776@gmail.com

120
DATA SCIENCE
INTERVIEW QUESTIONS

COMPILED AND CREATED BY:

CARL SHAN, MAX SONG, HENRY WANG, AND WILLIAM CHEN 1
 INTRODUCTION
This guide is meant to bridge the gap between the knowledge of a recent graduate and the skillset
required to become a data scientist. By reading this guide and learning how to answer these ques-
tions, recent graduates will equip themselves with the expected knowledge and skills of a data scien-
tist.

To help readers with these goals, we’ve gathered 120 interview questions in product metrics, pro-
gramming and databases, probability, experimentation and inference, data analysis, and predictive
modeling. These questions are all either real data science interview questions or inspired by real data
science interview questions, and should help readers develop the skills needed to succeed in a data
science role.

The role of a data scientist is highly malleable and company dependent. However, the general skillset
needed is similar. Candidates need:
• Technical skills - data analysis and programming
• Business/product intuition - metrics and identifying opportunities for impact
• Communication ability - clarity in explaining findings and insights

To prepare for your interview, you may want to brush up by reviewing some probability, data anal-
ysis, SQL, coding, and experimental design. The questions in this guide should help you do so. The
background of data science applicants varies wildly, so interviews may generally be more holistic and
test your intuition, analytic, and communication abilities rather than focusing on specific technical
concepts.

Prepare to discuss your past work involving analyzing large and complicated datasets, defending
your approaches and communicating what you learned during your project. Expect questions in-
volving how to measure “goodness” of a feature on the company’s product, and be sure to approach
these problems in a scientific and principled way. You have a good chance of getting a product
metrics or experimentation question based on some actual questions the company is tackling at this
time.

Check up on your company’s engineering / data blog and see if anything’s relevant. Be familiar with
A/B testing and common metrics that companies similar to the one you are interviewing for may
use. Brush up on your Python (especially iPython notebook) and/or R abilities to prepare for a po-
tential live data analysis problem.

And finally, of course, follow the general interview advice. Prepare to elaborate on related proj-
ects from your resume. Be enthusiastic. Share your thoughts with your interviewer as you’re going
through a problem or doing a piece of analysis. And be sure to answer the question!

You have our best wishes!

Carl, Max, Henry, and William

Please feel free to reach out to us with questions, comments and suggestions at www.datasciencehandbook.me
2
 CONTENTS
PREDICTIVE MODELING 4

PROGRAMMING 6

PROBABILITY 8

STATISTICAL INFERENCE 11

DATA ANALYSIS 13

PRODUCT METRICS 16

COMMUNICATION 18

DATA SCIENCE INTERVIEW QUESTIONS 3

 PREDICTIVE MODELING
1 (Given a Dataset) Analyze this dataset and give me a mod-
el that can predict this response variable.

2 What could be some issues if the distribution of the test

data is significantly different than the distribution of the
training data?

3 What are some ways I can make my model more robust

to outliers?

4 What are some differences you would expect in a model

that minimizes squared error, versus a model that min-
imizes absolute error? In which cases would each error
metric be appropriate?

5 What error metric would you use to evaluate how good

a binary classifier is? What if the classes are imbalanced?
What if there are more than 2 groups? PRO TIP
If asked to predict a response
6 What are various ways to predict a binary response vari- variable during your interview,
able? Can you compare two of them and tell me when you should favor simpler models
one would be more appropriate? What’s the difference that run quickly and which you
between these? (SVM, Logistic Regression, Naive Bayes, can easily explain. If the task is
Decision Tree, etc.) specifically a predictive model-
ing task, you should try to do,
7 What is regularization and where might it be helpful? or at least mention, cross-vali-
What is an example of using regularization in a model? dation as it really is the golden
standard to evaluate the qual-
8 Why might it be preferable to include fewer predictors ity of one’s model. Talk about
over many? and justify your approach while
you’re doing it, and leave some
9 Given training data on tweets and their retweets, how time to plot and visualize the
data.
would you predict the number of retweets of a given tweet
after 7 days after only observing 2 days worth of data?

10 How could you collect and analyze data to use social me-
dia to predict the weather?

DATA SCIENCE INTERVIEW QUESTIONS 4

 PREDICTIVE MODELING
11 How would you construct a feed to show relevant content
for a site that involves user interactions with items?

12 How would you design the people you may know feature
on LinkedIn or Facebook?

13 How would you predict who someone may want to send

a Snapchat or Gmail to?

14 How would you suggest to a franchise where to open a

new store?

15 In a search engine, given partial data on what the user has PRO TIP
typed, how would you predict the user’s eventual search Variations on ordinary linear re-
query? gression can help address some
problems that come up work-
16 Given a database of all previous alumni donations to your ing with read data. LASSO helps
when you have too many pre-
university, how would you predict which recent alumni are
dictors by favoring weights of
most likely to donate?
zero. Ridge regression can help
with reducing the variance of
17 You’re Uber and you want to design a heatmap to recom- your weights and predictions
mend to drivers where to wait for a passenger. How would by shrinking the weights to 0.
you approach this? Least absolute deviations or ro-
bust linear regression can help
18 How would you build a model to predict a March Mad- when you have outliers. Logis-
ness bracket? tic regression is used for binary
outcomes, and Poisson regres-
19 You want to run a regression to predict the probability sion can be used to model count
of a flight delay, but there are flights with delays of up to data.
12 hours that are really messing up your model. How can
you address this?

DATA SCIENCE INTERVIEW QUESTIONS 5

 PROGRAMMING
1 Write a function to calculate all possible assignment vec-
tors of 2n users, where n users are assigned to group 0
(control), and n users are assigned to group 1 (treatment).

2 Given a list of tweets, determine the top 10 most used

hashtags.

3 Program an algorithm to find the best approximate solu-

tion to the knapsack problem1 in a given time.

4 Program an algorithm to find the best approximate solu-

tion to the travelling salesman problem2 in a given time.

5 You have a stream of data coming in of size n, but you

don’t know what n is ahead of time. Write an algorithm
that will take a random sample of k elements. Can you PRO TIP
write one that takes O(k) space? Traditional software engineer-
ing questions may show up in
6 Write an algorithm that can calculate the square root of a data science interviews. Expect
number. those questions to be easier, less
about systems, and more about
7 Given a list of numbers, can you return the outliers? your ability to manipulate data,
read databases, and do simple
8 When can parallelism make your algorithms run faster? programming tasks. Review your
When could it make your algorithms run slower? SQL and prepare to do common
operations such as JOIN, GROUP
9 What are the different types of joins? What are the differ- BY, and COUNT. Review ways to
ences between them? manipulate data and strings (we
suggest doing this in Python), so
10 Why might a join on a subquery be slow? How might you you can answer questions that
speed it up? involve sifting through numeri-
cal or string data.
11 Describe the difference between primary keys and foreign
keys in a SQL database.

1 See http://en.wikipedia.org/wiki/Knapsack_problem
2 See http://en.wikipedia.org/wiki/Travelling_salesman_problem

DATA SCIENCE INTERVIEW QUESTIONS 6

 PROGRAMMING
12 Given a COURSES table with columns course_id and
course_name, a FACULTY table with columns facul-
ty_id and faculty_name, and a COURSE_FACULTY table
with columns faculty_id and course_id, how would
you return a list of faculty who teach a course given the
name of a course?

13 Given a IMPRESSIONS table with ad_id, click (an in-

dicator that the ad was clicked), and date, write a SQL
query that will tell me the click-through-rate of each ad
by month.

14 Write a query that returns the name of each department

and a count of the number of employees in each:

EMPLOYEES containing: Emp_ID (Primary key) and Emp_Name

EMPLOYEE_DEPT containing: Emp_ID (Foreign key) and Dept_
ID (Foreign key)
DEPTS containing: Dept_ID (Primary key) and Dept_Name

DATA SCIENCE INTERVIEW QUESTIONS 7

 PROBABILITY
1 Bobo the amoeba has a 25%, 25%, and 50% chance of
producing 0, 1, or 2 offspring, respectively. Each of Bobo’s
descendants also have the same probabilities. What is the
probability that Bobo’s lineage dies out?

2 In any 15-minute interval, there is a 20% probability that

you will see at least one shooting star. What is the proba-
bility that you see at least one shooting star in the period
of an hour?

3 How can you generate a random number between 1 - 7

with only a die?

4 How can you get a fair coin toss if someone hands you a
coin that is weighted to come up heads more often than
tails?

5 You have an 50-50 mixture of two normal distributions PRO TIP

with the same standard deviation. How far apart do the Important concepts to review
means need to be in order for this distribution to be bi- from an introductory probabili-
modal? ty class include the Law of Total
Probability, Bayes’ Rule, and Ex-
6 Given draws from a normal distribution with known pa- pectation. You can learn many of
rameters, how can you simulate draws from a uniform these topics (and important top-
distribution? ics regarding hypothesis testing
and inference) with intro-level
7 A certain couple tells you that they have two children, at courses in probability and infer-
least one of which is a girl. What is the probability that ence.
they have two girls?

8 You have a group of couples that decide to have children

until they have their first girl, after which they stop having
children. What is the expected gender ratio of the children
that are born? What is the expected number of children
each couple will have?

9 How many ways can you split 12 people into 3 teams of 4?

DATA SCIENCE INTERVIEW QUESTIONS 8

 PROBABILITY
10 Your hash function assigns each object to a number be-
tween 1:10, each with equal probability. With 10 objects,
what is the probability of a hash collision? What is the
expected number of hash collisions? What is the expected
number of hashes that are unused.

11 You call 2 UberX’s and 3 Lyfts. If the time that each takes
to reach you is IID, what is the probability that all the Ly-
fts arrive first? What is the probability that all the UberX’s
arrive first?

12 I write a program should print out all the numbers from 1

to 300, but prints out Fizz instead if the number is divisi-
ble by 3, Buzz instead if the number is divisible by 5, and
FizzBuzz if the number is divisible by 3 and 5. What is the
total number of numbers that is either Fizzed, Buzzed, or
FizzBuzzed?
PRO TIP
13 On a dating site, users can select 5 out of 24 adjectives Many Bayes’ Rule questions can
to describe themselves. A match is declared between two be solved quickly with the odds
users if they match on at least 4 adjectives. If Alice and form of Bayes Rule, which says
Bob randomly pick adjectives, what is the probability that that prior odds times likelihood
they form a match? ratio is the posterior odds. For
problem 18, the prior odds is
14 A lazy high school senior types up application and en- 999:1 and the likelihood ratio is
velopes to n different colleges, but puts the applications 1/1024:1 (10 heads has a 1/1024
randomly into the envelopes. What is the expected num- probability with a fair coin and a
1 probability with a biased coin),
ber of applications that went to the right college
which means the posterior odds
is about 1:1. For problem 19, the
15 Let’s say you have a very tall father. On average, what
prior odds is 1:1 and the likeli-
would you expect the height of his son to be? Taller, equal, hood ratio is 1/4:9/16, so the
or shorter? What if you had a very short father? posterior odds is 4:9.

16 What’s the expected number of coin flips until you get

two heads in a row? What’s the expected number of coin
flips until you get two tails in a row?

DATA SCIENCE INTERVIEW QUESTIONS 9

 PROBABILITY
17 Let’s say we play a game where I keep flipping a coin until I
get heads. If the first time I get heads is on the nth coin, then I
pay you 2n-1 dollars. How much would you pay me to play this
game?

18 You have two coins, one of which is fair and comes up heads
with a probability 1/2, and the other which is biased and comes
up heads with probability 3/4. You randomly pick coin and flip it
twice, and get heads both times. What is the probability that you
picked the fair coin?

19 You have a 0.1% chance of picking up a coin with both heads,

and a 99.9% chance that you pick up a fair coin. You flip your
coin and it comes up heads 10 times. What’s the chance that you
picked up the fair coin, given the information that you observed?

DATA SCIENCE INTERVIEW QUESTIONS 10

STATISTICAL INFERENCE
1 In an A/B test, how can you check if assignment to the
various buckets was truly random?

2 What might be the benefits of running an A/A test, where

you have two buckets who are exposed to the exact same
product?

3 What would be the hazards of letting users sneak a peek

at the other bucket in an A/B test?

4 What would be some issues if blogs decide to cover one

of your experimental groups?

5 How would you conduct an A/B test on an opt-in feature?

6 How would you run an A/B test for many variants, say 20
or more?

7 How would you run an A/B test if the observations are

PRO TIP
Proper A/B testing practices are
extremely right-skewed? often a common discussion,
especially because it easily be-
8 I have two different experiments that both change the comes more complicated than
sign-up button to my website. I want to test them at the anticipated in practice. Multiple
same time. What kinds of things should I keep in mind? variants and metrics, simultane-
ous conflicting experiments, and
9 What is a p-value? What is the difference between type-1 improper randomization will
and type-2 error? complicate experiments. Most
people do not have a formal ac-
10 You are AirBnB and you want to test the hypothesis that ademic background on experi-
a greater number of photographs increases the chances mental design.
that a buyer selects the listing. How would you test this
hypothesis?

11 How would you design an experiment to determine the

impact of latency on user engagement?

12 What is maximum likelihood estimation? Could there be

any case where it doesn’t exist?

DATA SCIENCE INTERVIEW QUESTIONS 11

STATISTICAL INFERENCE
13 What’s the difference between a MAP, MOM, MLE estima-
tor? In which cases would you want to use each?
PRO TIP
14 What is a confidence interval and how do you interpret it? Important concepts to know in-
clude randomization, Simpson’s
15 What is unbiasedness as a property of an estimator? Is this paradox, and multiple compar-
always a desirable property when performing inference? isons. Advanced concepts to
What about in data analysis or predictive modeling? know that may impress inter-
viewers includes alternatives to
A/B testing (such as multi-armed
bandit strategies), or alterna-
tives to t-tests and z-tests (e.g.
non-parametric methods, boot-
strapping)

DATA SCIENCE INTERVIEW QUESTIONS 12

 DATA ANALYSIS
1 (Given a Dataset) Analyze this dataset and tell me what
you can learn from it.

2 What is R2? What are some other metrics that could be

better than R2 and why?

3 What is the curse of dimensionality?

4 Is more data always better?

5 What are advantages of plotting your data before per-

forming analysis?

6 How can you make sure that you don’t analyze something
that ends up meaningless?

7 What is the role of trial and error in data analysis? What is

the the role of making a hypothesis before diving in? PRO TIP
Some concepts that are import-
8 How can you determine which features are the most im-
ant in data analysis and com-
portant in your model? mon in the field, include over-
fitting, regression towards the
9 How do you deal with some of your predictors being mean, curse of dimensionality,
missing? importance of visualization, and
inductive bias. These questions
10 You have several variables that are positively correlated test your knowledge and expe-
with your response, and you think combining all of the rience with some of the hazards
variables could give you a good prediction of your re- of blind data analysis and your
sponse. However, you see that in the multiple linear re- ability to distinguish a significant
gression, one of the weights on the predictors is negative. result from a spurious one.
What could be the issue?

11 Let’s say you’re given an unfeasible amount of predictors

in a predictive modeling task. What are some ways to
make the prediction more feasible?

12 Now you have a feasible amount of predictors, but you’re

fairly sure that you don’t need all of them. How would you
perform feature selection on the dataset?

DATA SCIENCE INTERVIEW QUESTIONS 13

 DATA ANALYSIS
13 Your linear regression didn’t run and communicates that
there are an infinite number of best estimates for the re-
gression coefficients. What could be wrong?

14 You run your regression on different subsets of your data,

and find that in each subset, the beta value for a certain
variable varies wildly. What could be the issue here?

15 What is the main idea behind ensemble learning? If I had

many different models that predicted the same response
variable, what might I want to do to incorporate all of the
models? Would you expect this to perform better than an
individual model or worse?

16 Given that you have wifi data in your office, how would
you determine which rooms and areas are underutilized
and overutilized?

17 How could you use GPS data from a car to determine the
quality of a driver?
PRO TIP
If asked to analyze a dataset
during the interview, the inter-
18 Given accelerometer, altitude, and fuel usage data from a viewer is looking to learn about
car, how would you determine the optimum acceleration your comfort with your statisti-
pattern to drive over hills? cal software and your ability to
generate interesting insights in
19 Given position data of NBA players in a season’s games, a short period of time. We rec-
how would you evaluate a basketball player’s defensive ommend making visualizations
ability? first, to show that you know
good practices, prevent future
20 How would you quantify the influence of a Twitter user? missteps, and identify possible
transformations needed. Be sure
21 Given location data of golf balls in games, how would to talk about your procedure
construct a model that can advise golfers where to aim? and anticipate questions about
your approach.
22 You have 100 mathletes and 100 math problems. Each
mathlete gets to choose 10 problems to solve. Given data
on who got what problem correct, how would you rank
the problems in terms of difficulty?

DATA SCIENCE INTERVIEW QUESTIONS 14

 DATA ANALYSIS
23 You have 5000 people that rank 10 sushis in terms of salt-
iness. How would you aggregate this data to estimate the
true saltiness rank in each sushi?

24 Given data on congressional bills and which congressio-

nal representatives co-sponsored the bills, how would you
determine which other representatives are most similar to
PRO TIP
Consider asking your interviewer
yours in voting behavior? How would you evaluate who is how data scientists extract and
the most liberal? Most republican? Most bipartisan? wrangle data at the company,
what tools the team uses to do
25 How would you come up with an algorithm to detect pla- its exploratory analysis, and how
giarism in online content? the company shares its findings
internally. Most of the work is
26 You have data on all purchases of customers at a grocery not the analysis. In fact, data sci-
store. Describe to me how you would program an algo- entists spend most of their time
rithm that would cluster the customers into groups. How just getting, cleaning, and pro-
would you determine the appropriate number of clusters cessing the data.
to include?

27 Let’s say you’re building the recommended music engine

at Spotify to recommend people music based on past lis-
tening history. How would you approach this problem?

DATA SCIENCE INTERVIEW QUESTIONS 15

 PRODUCT METRICS
1 What would be good metrics of success for an adver-
tising-driven consumer product? (Buzzfeed, YouTube,
Google Search, etc.) A service-driven consumer product?
(Uber, Flickr, Venmo, etc.)

2 What would be good metrics of success for a productiv-

ity tool? (Evernote, Asana, Google Docs, etc.) A MOOC?
(edX, Coursera, Udacity, etc.)

3 What would be good metrics of success for an e-com-

merce product? (Etsy, Groupon, Birchbox, etc.) A subscrip-
tion product? (Netflix, Birchbox, Hulu, etc.) Premium sub-
scriptions? (OKCupid, LinkedIn, Spotify, etc.)

4 What would be good metrics of success for a consumer

product that relies heavily on engagement and interac-
tion? (Snapchat, Pinterest, Facebook, etc.) A messaging
product? (GroupMe, Hangouts, Snapchat, etc.)
PRO TIP
5 What would be good metrics of success for a product The best choices of engagement
that offered in-app purchases? (Zynga, Angry Birds, other metrics are those that benefit
gaming apps) both the company and the us-
ers while correlating highly with
6 A certain metric is violating your expectations by going revenue. Pageviews and daily
actives would be appropriate
down or up more than you expect. How would you try to
for an advertising-driven prod-
identify the cause of the change? uct, and metrics such as number
of purchases or conversion rate
7 Growth for total number of tweets sent has been slow this would be appropriate for any
month. What data would you look at to determine the product that sells services and
cause of the problem? other products.

8 You’re a restaurant and are approached by Groupon to

run a deal. What data would you ask from them in order
to determine whether or not to do the deal?

9 You are tasked with improving the efficiency of a subway

system. Where would you start?

10 Say you are working on Facebook News Feed. What would

be some metrics that you think are important? How would
you make the news each person gets more relevant?

DATA SCIENCE INTERVIEW QUESTIONS 16

 PRODUCT METRICS
11 How would you measure the impact that sponsored sto-
ries on Facebook News Feed have on user engagement?
How would you determine the optimum balance between
sponsored stories and organic content on a user’s News
Feed?

12 You are on the data science team at Uber and you are
asked to start thinking about surge pricing. What would PRO TIP
be the objectives of such a product and how would you Interviewers are looking for can-
start looking into this? didates who have strong intu-
ition about metrics for success.
13 Say that you are Netflix. How would you determine what You should give many possible
metrics, each a bit more specif-
original series you should invest in and create?
ic than the previous. The inter-
viewer may stop and ask you to
14 What kind of services would find churn (metric that tracks
elaborate or describe how you
how many customers leave the service) helpful? How would collect or visualize the
would you calculate churn? data. Prepare to justify why the
metric is important, relevant,
15 Let’s say that you’re are scheduling content for a content and measurable.
provider on television. How would you determine the best
times to schedule content?

DATA SCIENCE INTERVIEW QUESTIONS 17

 COMMUNICATION
1 Explain to me a technical concept related to the role that
you’re interviewing for.

2 Introduce me to something you’re passionate about.

3 How would you explain an A/B test to an engineer with no

statistics background? A linear regression?

4 How would you explain a confidence interval to an engi-

neer with no statistics background? What does 95% con-
fidence mean?

5 How would you explain to a group of senior executives

why data is important?

6 Tell me about a data project that you’ve done with a team.

What did you add to the group?

7 Tell me about a dataset that you’ve analyzed. What tech-

PRO TIP
Interviews are about convincing
niques did you find helpful and which ones didn’t work? the interviewer that you know
what you’re talking about. Natu-
8 What’s your favorite algorithm? Can you explain it to me? rally, you will gain more ability to
do so with a better background
9 How could you help the generate public understanding in in the topics covered here.
towards the importance of using data to generate in- Practice teaching a concept, ex-
sights? plaining one of your past proj-
ects, and discussing your tech-
10 How would you convince a government agency to release niques.
their data in a publicly accessible API?

11 I’m a local business owner operating a small restaurant.

Convince me to switch my advertising budget from print
to internet.

DATA SCIENCE INTERVIEW QUESTIONS 18

DATA SCIENCE HANDBOOK
Knowing and being able to answer these questions will help you succeed in the data science
interview. But after landing that job, if you want to learn how to advance in your career as a data
scientist, you should check out The Data Science Handbook — a curated collection of interviews
containing advice and wisdom from some of top data scientists in the world.

You can get it at www.datasciencehandbook.me

DATA SCIENCE INTERVIEW QUESTIONS LAYOUT DESIGN BY: BRITTANY CHENG