Prepare for and practice interview questions from CHS across topics like Presentation, Statistics, SQL and more.

CHS Interview Questions

CHS Interview Guides

Machine Learning

How would we build a model to detect fraud and text customers to approve or deny fraudulent transactions

Bank Fraud Model

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

What are some reasons why measuring bias would be important in building this particular model

Food Delivery Times

How would you evaluate whether a decision tree is the right model and assess its performance before and after deployment

Decision Tree Evaluation

Data Structures & Algorithms

Given an integer N, write a function that returns all of the prime numbers up to N

Prime to N

Write a function moving_window to find the moving window average

Moving Window

Given a json string with nested objects, write a function that flattens all the objects to a single key-value dictionary.

Flatten JSON

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

Write a function to return True if two strings are anagrams of each other and False if they are not

Valid Anagram

Product Sense & Metrics

How would you measure the success of Facebook Groups

Group Success

How would you measure the success of the Instagram TV product

Instagram TV Success

What data points and metrics would you look at to decide if amateur creators are doing worse and only superstars do well

Amateur Performance

What are the top five metrics you would start tracking to understand the health of Google Docs

Docs Metrics

What are the most important metrics for WhatsApp

WhatsApp Metrics

Write a query to select the top 3 departments with at least ten employees and rank them according to the percentage of their employees making over 100K in salary.

Employee Salaries

Select the 2nd highest salary in the engineering department

2nd Highest Salary

Write a SQL query to count transactions filtered by several criterias.

Count Transactions

Write a query to get the duration in minutes of each ride longer than two hours, sorted descending

Time Difference

Write a query to find how much time each plane spent in the air each day in minutes rounded down

Total Time in Flight

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

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

Your Strengths and Weaknesses

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

Why Do You Want to Work With Us

Making data-driven insights actionable for those without technical expertise

Simple Explanations

Tell me about a project in which you had to clean and organize a large dataset.

Describing a real-world data cleaning and organization project

Data Cleaning Experiences

Analytics

Write a SQL query to select the 2nd highest salary in the engineering department.

Note: If more than one person shares the highest salary, the query should select the next highest salary.

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>departments</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>name</code></td>
<td>VARCHAR</td>
</tr>
</tbody>
</table>
Output:

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

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

Given a <code>employees</code> and <code>departments</code> table, select the top 3 departments with at least ten employees and rank them according to the percentage of their employees making over 100K in salary.

Example:

Input:

<code>employees</code> table

<table>
<thead>
<tr>
<th>Columns</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>departments</code> table

<table>
<thead>
<tr>
<th>Columns</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>
Output:

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

<tbody>
<tr>
<td><code>percentage_over_100k</code></td>
<td>FLOAT</td>
</tr>

<tr>
<td><code>department_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>number_of_employees</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>

Given an integer <code>N</code>, write a function that returns a list of all of the prime numbers up to <code>N</code>.

Note: Return an empty list there are no prime numbers less than or equal to <code>N</code>.

Example:

Input:

<pre tabindex="0" class="chroma"><code>N = 3
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def prime_numbers(N) -&gt; [2,3]
</code></pre>

Let’s say you work at an advertising firm. You have a table of users’ impressions of ad campaigns over time. Each <code>impression_id</code> consists of values of user engagement specified by <code>Excited</code>, <code>OK</code>, and <code>Bored</code>.

Write a query to find all users who were at some point “Excited” and have never been “Bored” with a campaign.

Example:

Input:

<code>ad_impressions</code> table:

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

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

<tr>
<td><code>dt</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>campaign_id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>impression_id</code></td>
<td>TEXT</td>
</tr>
</tbody>
</table>
Output:

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

<tbody>
<tr>
<td><code>user_id</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>

Write a query to find all users that were at some point "Excited" and have never been "Bored" with a campaign.

Always Excited Users

Let’s say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service in addition that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

How would we build this model?

Let’s say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

Which statement is true?

Let's say that you work at a bank that wants to build a model to detect fraud on the platform.

The bank wants to implement a text messaging service that will text customers when the model detects a fraudulent transaction in order for the customer to approve or deny the transaction with a text response.

Which statement is true?

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 you work at Costco. Costco has a database with two tables. The first is <code>users</code> composed of user information, including their registration date, and the second is <code>purchases</code> that has the entire item purchase history (if any) for those users.

Write a query to get the total amount spent on each item in the ‘purchases’ table by users that registered in 2022.

Example:

Input:

<code>users</code> table

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

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

<tr>
<td><code>user_name</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>registration_date</code></td>
<td>DATETIME</td>
</tr>
</tbody>
</table>
<code>purchases</code> table

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

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

<tr>
<td><code>user_id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>item</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>price</code></td>
<td>FLOAT</td>
</tr>

<tr>
<td><code>purchase_date</code></td>
<td>DATETIME</td>
</tr>
</tbody>
</table>
Output:

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

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

<tr>
<td><code>total_amount_spent</code></td>
<td>FLOAT</td>
</tr>
</tbody>
</table>

Total Spent on Products

Let’s say you work in air traffic control. You are given the table below containing information on flights between two cities.

Write a query to find out how much time, in minutes (rounded down), each plane spent in the air each day.

Note: Both cities are in the same time zone, so you do not need to worry about converting time zones.

<code>flights</code> table

Example:

Input:

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

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

<tr>
<td><code>destination_location</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>source_location</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>plane_id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>flight_start</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>flight_end</code></td>
<td>DATETIME</td>
</tr>
</tbody>
</table>
Output:

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

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

<tr>
<td><code>calendar_day</code></td>
<td>VARCHAR</td>
</tr>

<tr>
<td><code>time_in_min</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>
Please give <code>calendar_day</code> in the format <code>YYYY-MM-DD</code>

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

Let’s say you’re a Product Data Scientist at Instagram. How would you measure the success of the Instagram TV product?

What is the primary goal of Instagram TV as a product feature?

What is the primary goal of Instagram TV as a product feature?

How would you measure the success of Facebook Groups?

Considering the purpose of Facebook Groups as a platform for connecting users through shared interests or real-life relationships, which metrics would be appropriate to measure the success of these groups?

Considering the purpose of Facebook Groups as a platform for connecting users through shared interests or real-life relationships, which metrics would be appropriate to measure the success of these groups?

You’re given a string that may contain the characters <code>{</code>, <code>}</code>, <code>[</code>, <code>]</code>, <code>(</code>, and <code>)</code>.

Task: Verify that the string is balanced. A balanced string is one where every opening character, <code>{</code>, <code>[</code>, or <code>(</code>, has a corresponding closing character, <code>}</code>, <code>]</code>, or <code>)</code>.

Write a function called <code>is_balanced(string: str) -&gt; bool</code> which verifies the balance of a string.

Example:

<pre tabindex="0" class="chroma"><code>is_balanced(&#39;(())[]{}&#39;) -&gt; True
</code></pre>

<pre tabindex="0" class="chroma"><code>is_balanced(&#39;{([(){}])()}&#39;) -&gt; True
</code></pre>

<pre tabindex="0" class="chroma"><code>is_balanced(&#39;{}[]())&#39;) -&gt; False
</code></pre>

<hr/>

Write a function that tests whether a string of brackets is balanced.

The Brackets Problem

How does random forest generate the forest? Additionally, why would we use it over other algorithms such as logistic regression?

What happens when you average the output on multiple decision trees?

What happens when you average the output on multiple decision trees?

Average Trees

How does random forest generate the forest and why use it over logistic regression

Random Forest Explanation

You are a data scientist at YouTube focused on creators.

A PM comes to you worried that amateur video creators could do well before but now it seems like only “superstars” do well.

What data points and metrics would you look at to decide if this is true or not?

You work at a ride-sharing company and are given a table containing information about the rides of users.

Write a query to get the duration (in minutes) of each ride longer than two hours. Sort the results by duration in descending order.

<code>rides</code> table:

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

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

<tr>
<td><code>passenger_user_id</code></td>
<td>INTEGER</td>
</tr>

<tr>
<td><code>start_dt</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>end_dt</code></td>
<td>DATETIME</td>
</tr>

<tr>
<td><code>distance</code></td>
<td>FLOAT</td>
</tr>

<tr>
<td><code>ride_region</code></td>
<td>VARCHAR</td>
</tr>

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

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

<tbody>
<tr>
<td><code>duration_minutes</code></td>
<td>INTEGER</td>
</tr>
</tbody>
</table>

You are given a binary tree of unique positive numbers. Each node in the binary tree is represented as a dictionary with the following keys:

<ul>
<li><code>data</code>: integer value stored in the node</li>
<li><code>left</code>: reference to the left child (or <code>None</code>)</li>
<li><code>right</code>: reference to the right child (or <code>None</code>)</li>
</ul>

<pre tabindex="0" class="chroma"><code>node = {
 &#34;data&#34;: 6,
 &#34;left&#34;: {
 &#34;data&#34;: 3,
 &#34;left&#34;: {...},
 &#34;right&#34;: {...}
 },
 &#34;right&#34;: {
 &#34;data&#34;: 9,
 &#34;left&#34;: {...},
 &#34;right&#34;: {...}
 }
}
</code></pre>

Given two node values as input (<code>value1</code> and <code>value2</code>), write a function to return the value of the nearest common ancestor (lowest node in the tree that has both nodes as descendants).

Note: If one of the nodes doesn’t exist in the tree, return <code>-1</code>.

Example:

Input:

<pre tabindex="0" class="chroma"><code># Diagram of the binary tree
&#39;&#39;&#39;
 6 
 / \ 
 3 9 
 / \
 2 11
 / \
 5 8
&#39;&#39;&#39;
value1 = 8
value2 = 2
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>common_ancestor(root,value1,value2) -&gt; 3
</code></pre>

Explanation:

<ul>
<li>Ancestors of <code>8</code>: <code>11 → 3 → 6</code></li>
<li>Ancestors of <code>2</code>: <code>3 → 6</code></li>
<li>Common ancestors: <code>3</code> and <code>6</code></li>
<li>The nearest common ancestor is <code>3</code>.</li>
</ul>

Write a function to return the value of the nearest node that is a parent to both nodes.

Nearest Common Ancestor

Let’s say you’re interning at a fintech startup that’s building a platform for online games of chance. During testing, one of your simulations flips a coin 10 times and gets 8 tails and 2 heads.

How would you determine if the coin is fair, and what statistical approach would you use to support your conclusion?

How would you assess if a coin is fair after observing 8 tails in 10 flips?

Fair Coin

Probability

A group of 100 students are participating in a coin-tossing challenge at a school event. Each student flips a fair coin once:
- If the coin lands on heads, the student wins and truthfully reports their win.
- If the coin lands on tails, the student flips again:
 - If the second flip is heads, the student lies and claims they won, even though they lost.
 - If the second flip is tails, the student truthfully reports their loss.

At the end of the game, 30 students report that they won. As an analyst, you are tasked with determining the expected number of students who actually won the game (i.e., got heads on their first flip).

Example:

Suppose only 8 students report winning. How many students would you expect to have truly won based on the rules above?

Note: You may assume each coin flip is independent and fair (probability of heads = 0.5).

Given win reports in a coin toss game with lying, estimate the true number of winners.

Secret Wins

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.

Given two strings, write a function to return <code>True</code> if the strings are anagrams of each other and <code>False</code> if they are not.

Note: A word is not an anagram of itself.

Example 1:

Input:

<pre tabindex="0" class="chroma"><code>string_1 = &#34;listen&#34;
string_2 = &#34;silent&#34;
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>True
</code></pre>

Example 2:

Input:

<pre tabindex="0" class="chroma"><code>string_1 = &#34;banana&#34;
string_2 = &#34;bandana&#34;
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>False
</code></pre>

Given a <code>JSON</code> string with nested objects, write a function <code>flatten_json</code> that flattens all the objects to a single key-value dictionary. Do not use the library that actually performs this function.

Example:

Input:

<pre tabindex="0" class="chroma"><code>import json
json_str = json.dumps({&#39;a&#39;:{&#39;b&#39;:&#39;c&#39;, &#39;d&#39;:&#39;e&#39;}})
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def flatten_json(json_str) -&gt; json.dumps({&#39;a_b&#39;:&#39;c&#39;, &#39;a_d&#39;:&#39;e&#39;})
</code></pre>

Note: Input and output are in <code>string</code> format : use <code>json.dumps()</code> to convert python dictionary to string.

You’re AI engineer working on an energy forecasting system at Siemens that helps utilities predict short-term electricity demand to balance grid load and reduce outages. You train a recurrent neural network on long historical time series (weather, calendar effects, local demand signals) to forecast energy demand.

Early in training, the model appears to learn normally, but after several epochs the loss becomes highly unstable, oscillating wildly before turning into NaNs. At the same time, training slows dramatically and the model fails to recover even after restarting from recent checkpoints.

You’ve verified that the data pipeline is correct and labels are well-aligned with inputs. No changes were made to the dataset, but increasing the sequence length or learning rate makes the problem significantly worse.

How would you investigate the cause of this training instability? What signals would you look for during debugging, and how would those findings guide the changes you make to the model or training setup?

How would you investigate the cause of this training instability?

Training Instability in Neural Networks

Suppose there exists a new airline named Jetco that flies domestically across North America. Jetco recently had a study commissioned that tested the boarding time of every airline, and it came out that Jetco had the fastest average boarding times of any airline.

What factors could have biased this result, and what would you look into?

What could potentially bias the average boarding time in favor of an airline that only flies domestically?

What could potentially bias the average boarding time in favor of an airline that only flies domestically?

Boarding Times Bias

A new airline came out as the fastest average boarding times compared to other airlines.  What factors could have biased this result and what would you look into?

Statistics

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

Given a table of <code>cars</code> with columns <code>id</code> and <code>make</code>, write a query that outputs a random manufacturer’s name with an equal probability of selecting any name.

Input:

<code>cars</code> table

<table>
<thead>
<tr>
<th><code>id</code></th>
<th><code>make</code></th>
</tr>
</thead>

<tbody>
<tr>
<td>1</td>
<td>Ford</td>
</tr>

<tr>
<td>2</td>
<td>Toyota</td>
</tr>

<tr>
<td>3</td>
<td>Toyota</td>
</tr>

<tr>
<td>4</td>
<td>Honda</td>
</tr>

<tr>
<td>5</td>
<td>Honda</td>
</tr>

<tr>
<td>6</td>
<td>Honda</td>
</tr>
</tbody>
</table>
Output:

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

<tbody>
<tr>
<td><code>make</code></td>
<td>Text</td>
</tr>
</tbody>
</table>

Write a query that outputs a random manufacturer's name with an equal probability of selecting any name.

Uniform Car Maker

How would you handle the data preparation for building a machine learning model using imbalanced data?

Addressing imbalanced data in machine learning through carefully prepared techniques.

Data Preparation for Imbalanced Data

Let’s say that you work as a data scientist at a food delivery company.

You are tasked with building a model to predict food preparation times at a restaurant from the time when a customer sends in the order to when the meal is ready for the driver to pick up.

What are some reasons why measuring bias would be important in building this particular model?

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

What are the assumptions of linear regression?

Assumptions of Linear Regression

You are given a <code>string</code> that represents some floating-point number. Write a function, <code>digit_accumulator</code>, that returns the sum of every digit in the <code>string</code>.

Example:

Input:

<pre tabindex="0" class="chroma"><code>s = &#34;123.0045&#34;
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def digit_accumulator(s) -&gt; 15

Since 
1 + 2 + 3 + 0 + 0 + 4 + 5 = 15
</code></pre>

Write a function digit_accumulator that returns the sum of every digit in a string

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

CHS Interview Questions

CHS Interview Guides

CHS Interview Questions

Challenge

CHS Salaries by Position

Discussion & Interview Experiences

Discussion & Interview Experiences