Prepare for and practice interview questions from United Nations.

United Nations Interview Questions

United Nations Interview Guides

A/B Testing

How would you assess the validity of the result?

Experiment Validity

How would you determine if the new model predicts delivery times better than the old model

Delivery Estimate Model

Button AB Test

A/B Test Power Size

How would you make a control group and test group to account for network effects

Network Experiment Design

Machine Learning

Which model would perform better and why?

Booking Regression

Lasso vs Ridge

In which case would you use a bagging algorithm versus a boosting algorithm

Bagging vs Boosting

What are the logistic and softmax functions? What is the difference between the two?

Softmax vs Logistic

Which model do you pick given 85% and 82% accuracy

85% vs 82%

Data Structures & Algorithms

Given two sorted lists, write a function to merge them into one sorted list.

Merge Sorted Lists

Find the missing integer from a array of consequtive integers

Find the Missing Number

Write a function one_element_removed that returns the integer removed from list Y in O(1) space and O(n) time without using set

One Element Removed

Given an array and a target integer, write a function that returns the indices of two integers in the array that add up to the target integer.

Target Indices

This problem involves identifying duplicate numbers in a list of integers. The function should return a list of the duplicate numbers.

Find Duplicate Numbers in a List

Statistics

Say you are given a dataset of perfectly linearly separable data. What would happen when you run logistic regression?

Perfectly Separable

How many more samples are needed to decrease the margin of error to 0.3

Reducing Error Margin

What are the assumptions of linear regression?

Assumptions of Linear Regression

Explain what an unbiased estimator is and provide a layman-friendly example

Unbiased Estimator

How do you detect and handle correlation between variables in linear regression, and what happens if you ignore it

Correlation in Regression

Behavioral

Describing a data project and its challenges

Hurdles In Data Projects

Strategically resolving misaligned expectations with stakeholders for a successful project outcome

Stakeholder Communication

How would you answer when an Interviewer asks why you applied to their company?

Why Do You Want to Work With Us

What do you tell an interviewer when they ask you what your strengths and weaknesses are?

Your Strengths and Weaknesses

Making data-driven insights actionable for those without technical expertise

Simple Explanations

Given two sorted lists, write a function to merge them into one sorted list.

Bonus: What’s the time complexity?

Example:

Input:

<pre tabindex="0" class="chroma"><code>list1 = [1,2,5]
list2 = [2,4,6]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def merge_list(list1,list2) -&gt; [1,2,2,4,5,6]
</code></pre>

You have two sorted lists, one with m elements and one with n elements. What would be the time complexity of merging the two lists via merge sort?

You have two sorted lists, one with m elements and one with n elements. What would be the time complexity of merging the two lists via merge sort? 

Merging Lists Complexity

Let’s say that your company is running a standard control and variant AB test on a feature to increase conversion rates on the landing page. The PM checks the results and finds a .04 p-value.

How would you assess the validity of the result?

Let’s say you want to test the close friends feature on Instagram Stories.

How would you make a control group and test group to account for network effects?

What could be a potential risk when Facebook segments the metrics of the user interface change by market or demographic groups?

What could be a potential risk when Facebook segments the metrics of the user interface change by market or demographic groups?

Network Experiment Design I

What is the primary metric that Facebook should monitor if it decides to make the user interface of its posting feature more like Instagram's?

What is the primary metric that Facebook should monitor if it decides to make the user interface of its posting feature more like Instagram's?

Network Experiment Design II

If Facebook changes its user interface to mimic Instagram's, which adverse effect should they anticipate and monitor?

If Facebook changes its user interface to mimic Instagram's, which adverse effect should they anticipate and monitor?

Network Experiment Design III

You have an array of integers, <code>nums</code> of length <code>n</code> spanning <code>0</code> to <code>n</code> with one missing. Write a function <code>missing_number</code> that returns the missing number in the array.

Note: Complexity of \(O(n)\) required.

Example:

Input:

<pre tabindex="0" class="chroma"><code>nums = [0,1,2,4,5] 
missing_number(nums) -&gt; 3
</code></pre>

A team wants to A/B test multiple different changes through a sign-up funnel.

For example, on a page, a button is currently red and at the top of the page. They want to see if changing a button from red to blue and/or from the top of the page to the bottom of the page will increase click-through.

How would you set up this test?

Your team wants to run an AB test on the color (red or blue) and position (top/bottom of the page) of a button that links to a promotion.

How many different variants of the test should you run to see the effect that a red button has on the bottom of the page, if currently the button is blue and on the top of the page.

Your team wants to run an AB test on the color (red or blue) and position (top/bottom of the page) of a button that links to a promotion.

How many different variants of the test should you run to see the effect that a red button has on the bottom of the page, if currently the button is blue and on the top of the page.

A/B Test Variants

There are two lists, <code>list X</code> and <code>list Y</code>. Both lists contain integers from <code>-1000</code> to <code>1000</code> and are identical to each other except that one integer is removed in <code>list Y</code> that exists in <code>list X</code>.

Write a function <code>one_element_removed</code> that takes in both lists and returns the integer that was removed in \(O(1)\) space and \(O(n)\) time without using the python set function.

Example:

Input:

<pre tabindex="0" class="chroma"><code>list_x = [1,2,3,4,5]
list_y = [1,2,4,5]

one_element_removed(list_x, list_y) -&gt; 3
</code></pre>

Which of the following methods would be the most efficient way of identifying what element is not included in two lists of integers that differ by a single element being removed?

For example, if the lists are <code>[1,2,3,4,5]</code> and <code>[1,2,4,5]</code>, the function should return <code>3</code>

Which of the following methods would be the most efficient way of identifying what element is not included in two lists of integers that differ by a single element being removed? 

For example, if the lists are `[1,2,3,4,5]` and `[1,2,4,5]`, the function should return `3`

Efficiently Identifying Missing Integer

Let’s say we have a sample size of \(n\). The margin of error for our sample size is 3.

How many more samples would we need to decrease the margin of error to 0.3?

Let's say we have a sample size of N. The margin of error for our sample size is 3.

How many more samples would we need to decrease the margin of error to 0.3?

Let's say we have a sample size of N. The margin of error for our sample size is 3.

How many more samples would we need to decrease the margin of error to 0.3?

Let’s say you’re playing a dice game. You have 2 dice.

<ol>
<li>What’s the probability of rolling at least one 3?</li>

<li>What’s the probability of rolling at least one 3 given \(N\) dice?</li>
</ol>

What's the probability of rolling at least one 3 with two dice?

What's the probability of rolling at least one 3 with two dice?

N Dice

Solve the probability of rolling 3s with n-dice.

Probability

Say you are given a dataset of perfectly linearly separable data.

What would happen when you run logistic regression?

What happens when logistic regression is run on a dataset of perfectly linearly separable data?

What happens when logistic regression is run on a dataset of perfectly linearly separable data?

Let’s say that you work at a B2B SAAS company that’s interested in testing the pricing of different levels of subscriptions.

Your project manager comes to you and asks you to run a two-week-long A/B test to test an increase in pricing.

How would you approach designing this test? How would you determine whether the increase in pricing is a good business decision?

How would you design a two-week A/B test to determine whether a pricing increase is a good business decision

Testing Price Increase

Over budget on a project is defined when the salaries, prorated to the day, exceed the budget of the project.

For example, if Alice and Bob both combined income make 200K and work on a project of a budget of 50K that takes half a year, then the project is over budget given 0.5 * 200K = 100K &gt; 50K.

Write a query to forecast the budget for all projects and return a label of <code>&#34;overbudget&#34;</code> if it is over budget and <code>&#34;within budget&#34;</code> otherwise.

Note: Assume that employees only work on one project at a time.

Example:

Input:

<code>employees</code> table

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>first_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>last_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>salary</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>department_id</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>
<code>projects</code> table

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>title</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>state_date</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>end_date</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>budget</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>
departments table

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>name</code></td>
<td>VARCHAR</td>
</tr>
</tbody>
</table>
<code>employee_projects</code> table

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>project_id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>employee_id</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>
Output:

<table>
<thead>
<tr>
<th>Column</th>
<th>Type</th>
</tr>
</thead>

<tbody>
<tr>
<td><code>title</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>project_forecast</code></td>
<td>VARCHAR</td>
</tr>
</tbody>
</table>

Write a query to forecast each project's budget and label it overbudget or within budget

Over-Budget Projects

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

In an A/B test, which of the following is a common method to determine if the assignment to the test groups was truly random?

In an A/B test, which of the following is a common method to determine if the assignment to the test groups was truly random?

Random Bucketing

How can you check if assignment to the various buckets was truly random

Let’s say we want to build a model to predict booking prices on Airbnb.

Between linear regression and random forest regression, which model would perform better and why?

What are the two key concepts of random forest regression?

What are the two key concepts of random forest regression?

Given a list of integers, identify all the duplicate values in the list. Assume that the list can contain both positive and negative numbers, and the order of the list does not matter. A number is considered a duplicate if it appears more than once in the list. Return a list of the duplicate numbers.

Example 1:

Input:

<pre tabindex="0" class="chroma"><code>nums = [1, 2, 3, 1, 2, 3]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>find_duplicates(nums) -&gt; [1, 2, 3]
</code></pre>

The numbers 1, 2, and 3 all appear more than once in the list, so they are considered duplicates.

Example 2:

Input:

<pre tabindex="0" class="chroma"><code>nums = [1, -1, 2, 3, 3, -1]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>find_duplicates(nums) -&gt; [-1, 3]
</code></pre>

The numbers -1 and 3 both appear more than once in the list, so they are considered duplicates. Note that the order of the output does not matter.

Example 3:

Input:

<pre tabindex="0" class="chroma"><code>nums = [1, 2, 3, 4, 5]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>find_duplicates(nums) -&gt; []
</code></pre>

None of the numbers in the list appear more than once, so there are no duplicates.

Tell me about a data project that didn’t go the way you expected. What did you set out to do, what surprised you, and how did you handle it?

Let’s say we’re comparing two machine learning algorithms. In which case would you use a bagging algorithm versus a boosting algorithm? 

Give an example of the tradeoffs between the two.

In machine learning, when would you use a bagging algorithm over a boosting algorithm?

In machine learning, when would you use a bagging algorithm over a boosting algorithm?

Bagging vs. Boosting

Given an array and a target integer, write a function <code>sum_pair_indices</code> that returns the indices of two integers in the array that add up to the target integer. If not found, just return an empty list.

Note: Can you do it on \(O(n)\) time?

Note: Even though there could be many solutions, only one needs to be returned.

Example 1:

Input:

<pre tabindex="0" class="chroma"><code>array = [1 2 3 4] 
target = 5 
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def sum_pair_indices(array, target) -&gt; [0 3] or [1 2]
</code></pre>

Example 2:

Input:

<pre tabindex="0" class="chroma"><code>array = [3]
target = 6 
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>Do NOT return [0 0] as you can&#39;t use an index twice.
</code></pre>

Let’s say we want to build a new delivery time estimate model for consumers ordering food delivery.

How would you determine if the new model predicts delivery times better than the old model?

When rolling out a new delivery time estimate model in production, what is an important consideration?

When rolling out a new delivery time estimate model in production, what is an important consideration?

Delivery Estimate Model I

What is one way to measure the performance of a new delivery time estimate model for food delivery?

What is one way to measure the performance of a new delivery time estimate model for food delivery?

Delivery Estimate Model II

What’s the difference between Lasso and Ridge Regression?

Under what circumstances is it recommended to use Lasso regression over Ridge regression?

Under what circumstances is it recommended to use Lasso regression over Ridge regression?

Let’s say you’re a data scientist at LinkedIn where you’re working on a product that sends qualified job candidates to companies. The team has launched a new feature that allows candidates to message hiring managers at companies directly during the interview process to get updates on their status.

Due to engineering constraints, the company can’t AB test the feature before launching it.

How would you analyze how the feature is performing?

How would you analyze the performance of a new LinkedIn feature that lets candidates message hiring managers during the interview process

Recruiting Leads

Analytics

You’re a data scientist at YouTube. Leadership wants to revisit how the platform measures success, not for a specific new feature, but for the product as a whole given its current state.

How would you define and measure success for YouTube? Identify your primary and secondary metrics, explain your rationale for each, and discuss how you would choose the right thresholds for any engagement-based metrics you propose.

The role of A/B testing in measuring the success rate of an analytics experiment

Success Measurement

Product Sense & Metrics

What are the assumptions of linear regression?

Which assumption of the residuals of the standard linear regression model can not be overcome by increasing the sample size?

Regression assumptions

Design a database to represent a Tinder style dating app. 

What does the schema look like and what are some optimizations that you think we might need?

Let’s say you are making a swiping app, similar to Tinder.

What would be the most efficient way (in terms of retrieval time) to store which users have swiped on each other on a database backend?

Let's say you are making a swiping app, similar to Tinder.

What would be the most efficient way (in terms of retrieval time) to store which users have swiped on each other on a database backend?

Swipes Database Design

Design a database schema for a Tinder-style dating app and discuss needed optimizations

Swiping App Design

Data Modeling

What is an unbiased estimator and can you provide an example for a layman to understand?

What makes an estimator of a population statistic unbiased?

Let’s say you have to analyze the results of an AB test.

One variant of the AB test has a sample size of 50K users and the other has a sample size of 200K users.

Given the unbalanced size between the two groups, can you determine if the test will result in bias towards the smaller group?

Given an AB test where one variant has a sample size of 50K users and the other has a sample size of 200K users, what is the likely effect of the unbalanced sizes on the test results?

Given an AB test where one variant has a sample size of 50K users and the other has a sample size of 200K users, what is the likely effect of the unbalanced sizes on the test results?

Sample Size Bias

Can you determine if the test will result in bias towards the smaller group?

Let’s say we’re testing a new UI with the goal to increase conversion rates. We test it by giving the new UI to a random subset of users.

The test variant wins by 5% on the target metric. What would you expect to happen after the new UI is applied to all users? Will the metric actually go up by ~5%, more, or less?

Note: Assume there is no novelty effect.

What would you expect to happen after the new UI is applied to all users?

New UI Effect

Uber Rider deals with huge amounts of data but at Uber Fleet, the amount of data for experimentation is rather low. Let’s say you run an AB test for Uber Fleet and find out that the distribution is not normal.

What kind of analysis would you run and how would you measure which variant won?

Which of the following is NOT an acceptable way to deal with AB testing on a non-normally distributed population?

Which of the following is NOT an acceptable way to deal with AB testing on a non-normally distributed population?

Non-Normal AB Test

What kind of analysis would you run and how would you measure which variant won

Non-Normal AB Testing

What are the logistic and softmax functions? What is the difference between the two?

What makes them useful for use in logistic regression?

In logistic regression, how is the predicted class determined based on the logistic function?

In logistic regression, how is the predicted class determined based on the logistic function?

Softmax vs Logistic II

What is the key characteristic of the logistic function that makes it useful for mapping continuous values to a probability?

What is the key characteristic of the logistic function that makes it useful for mapping continuous values to a probability?

Softmax vs Logistic I

Let’s say you are tasked with building a spam classifier for emails. Assume that you’ve built a V1 of the model.

What metrics would you use to track accuracy and validity of the model?

What metrics would you use to track accuracy and validity of the model

Spam Classifier 

Imagine you are asked to build a machine learning model to decide new loan approvals for a
financial firm. You ask the data department in the company for a subset of data to get started
working on the problem. The data includes different features about applicants such as age,
occupation, zip code, height, number of children, favorite color, etc. You decide to build
multiple machine learning models to test out different ideas before settling on the best one.

How would you explain the bias-variance tradeoff with regards to
building and choosing a model to use?

Calculate Moving Average	SQL	Easy
Predict Customer Churn	Machine Learning	Medium
A/B Test Significance	Statistics	Medium
Optimize Query Performance	SQL	Hard
Feature Importance Analysis	Machine Learning	Medium
Clean Missing Data	Python	Easy
Neural Network Architecture	Deep Learning	Hard
Calculate Cohort Retention	SQL	Medium
Bayesian Probability	Statistics	Easy
Recommend Similar Products	Machine Learning	Hard

United Nations Interview Questions

United Nations Interview Guides

United Nations Interview Questions

Challenge

Discussion & Interview Experiences

Discussion & Interview Experiences