Prepare for and practice interview questions from Cubic Corporation.

Cubic Corporation Interview Questions

Cubic Corporation Interview Guides

Machine Learning

Build a k Nearest Neighbors classification model from scratch.

KNN From Scratch

Explain Neural Nets to Kids

Where k=1, write a KNN algorithm from scratch.

A Simpler KNN From Scratch

Business Case

How would you balance production speed and employee satisfaction when considering a switch to robotics?

Robotics Upgrade Tradeoff

Find top frequent flights between source and destination.

Flight Routes - 2

Behavioral

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

Your Strengths and Weaknesses

Statistics

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?

Boarding Times Bias

When an interviewer asks a question along the lines of:

<ul>
<li>What would your current manager say about you? What constructive criticisms might he give?</li>
<li>What are your three biggest strengths and weaknesses you have identified in yourself?</li>
</ul>

How would you respond?

When asked about your strengths in an interview, what is an effective way to respond?

When asked about your strengths in an interview, what is an effective way to respond?

Your Strengths and Weaknesses I

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Your Strengths and Weaknesses II

One day you are invited to your kid’s kindergarten. The children there ask about your work as a machine learning engineer.

How would you explain neural networks to the kids there?

Build a \(k\) Nearest Neighbors classification model from scratch with the following conditions:

<ul>
<li>Use Euclidian distance (aka, the “2 norm”) as your closeness metric</li>
<li>Your function should be able to handle data frames of arbitrary many rows and columns</li>
<li>If there is a tie in the class of the \(k\) nearest neighbors, rerun the search using \(k-1\) neighbors instead</li>
<li>You may use <code>pandas</code> and <code>numpy</code> but NOT <code>scikit-learn</code></li>
</ul>

Example:

Input:

<pre tabindex="0" class="chroma"><code>k = 5
new_point = [0.5,-2,8]
print(data)
...
 Var1 Var2 Var3 Target
0 -3.279536 3.362223 2.847892 2
1 -0.791565 1.742475 2.151587 2
2 -0.785992 -0.938681 -0.459770 0
3 -1.068190 1.461051 0.127130 3
4 -0.367568 -0.870240 -0.225734 0
.. ... ... ... ...
95 -1.327175 1.971085 -0.690689 2
96 -3.203714 1.847649 0.778901 2
97 -0.587640 0.647458 2.094385 2
98 0.363644 -0.509795 2.514191 1
99 -0.673498 2.955285 2.102122 4

[100 rows x 4 columns]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def kNN(k, new_point, data) -&gt; 2
</code></pre>

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?

Write a function <code>knn</code> which returns the nearest data point from a list of data points to a given query point. Use Euclidean distance as the similarity measure. For the purpose of this task, consider the scenario where \( k=1 \), meaning you only need to find the single closest data point.

Note: Using external libraries such as numpy and scikit-learn is not allowed.

Example:

Input:

<pre tabindex="0" class="chroma"><code>data_points = [
[1, 2, 3],
[4, 5, 6],
[7, 8, 9]
]

querying_point = [1, 9, 7]
</code></pre>

Output:

<pre tabindex="0" class="chroma"><code>def knn(data_point: List[List[float]], query_point: List[float]) -&gt; [4, 5, 6] 
</code></pre>

Let’s say we manage a factory where the current manual production line employs 50 workers, and we have the option to upgrade to a robotic system that can produce parts at 3 times the current rate.

How would you approach deciding between upgrading to robotics or keeping the manual line, if our goals are to minimize total production time while also maintaining high employee satisfaction?

Delta Airlines is analyzing how passengers travel across its domestic network. The analytics team wants to understand which routes are most commonly flown out of each airport, and how long these popular journeys usually take. You’re working as a data analyst at Delta Airlines, and you’re provided with a table <code>flights</code> where each row represents one scheduled flight.

Write a SQL query to return the top 5 most frequent flight routes for each origin, ordered first by frequency descending, and then (for ties) by average journey duration ascending.

Notes:

<ol>
<li>A route is defined as a unique <code>(origin, destination)</code> pair.</li>
<li>Assume there is no more then 5 routes with the same frequency and average filght time.</li>
</ol>

<h2>Schema:</h2>

Input:

<h3><code>flights</code></h3>

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

<tbody>
<tr>
<td>flight_id</td>
<td>INTEGER</td>
</tr>

<tr>
<td>origin</td>
<td>VARCHAR</td>
</tr>

<tr>
<td>destination</td>
<td>VARCHAR</td>
</tr>

<tr>
<td>departure_time</td>
<td>DATETIME</td>
</tr>

<tr>
<td>arrival_time</td>
<td>DATETIME</td>
</tr>
</tbody>
</table>
Output:

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

<tbody>
<tr>
<td>origin</td>
<td>VARCHAR</td>
</tr>

<tr>
<td>destination</td>
<td>VARCHAR</td>
</tr>

<tr>
<td>route_frequency</td>
<td>INTEGER</td>
</tr>

<tr>
<td>avg_duration_minutes</td>
<td>DATETIME</td>
</tr>
</tbody>
</table>

<h2>Example:</h2>

<h3>Input Data</h3>

<h3><code>flights</code></h3>

<table>
<thead>
<tr>
<th>flight_id</th>
<th>origin</th>
<th>destination</th>
<th>departure_time</th>
<th>arrival_time</th>
</tr>
</thead>

<tbody>
<tr>
<td>1</td>
<td>JFK</td>
<td>LAX</td>
<td>2025-11-19 08:00</td>
<td>2025-11-19 11:30</td>
</tr>

<tr>
<td>2</td>
<td>JFK</td>
<td>LAX</td>
<td>2025-11-19 14:00</td>
<td>2025-11-19 17:40</td>
</tr>

<tr>
<td>3</td>
<td>JFK</td>
<td>ORD</td>
<td>2025-11-19 09:00</td>
<td>2025-11-19 10:45</td>
</tr>

<tr>
<td>4</td>
<td>JFK</td>
<td>ORD</td>
<td>2025-11-20 09:00</td>
<td>2025-11-20 10:42</td>
</tr>

<tr>
<td>5</td>
<td>JFK</td>
<td>MIA</td>
<td>2025-11-19 12:00</td>
<td>2025-11-19 15:00</td>
</tr>

<tr>
<td>6</td>
<td>JFK</td>
<td>MIA</td>
<td>2025-11-20 12:00</td>
<td>2025-11-20 14:55</td>
</tr>

<tr>
<td>7</td>
<td>LAX</td>
<td>SFO</td>
<td>2025-11-19 07:00</td>
<td>2025-11-19 08:25</td>
</tr>

<tr>
<td>8</td>
<td>LAX</td>
<td>SFO</td>
<td>2025-11-19 16:00</td>
<td>2025-11-19 17:20</td>
</tr>

<tr>
<td>9</td>
<td>LAX</td>
<td>SEA</td>
<td>2025-11-19 06:00</td>
<td>2025-11-19 08:40</td>
</tr>

<tr>
<td>10</td>
<td>LAX</td>
<td>SEA</td>
<td>2025-11-20 06:00</td>
<td>2025-11-20 08:35</td>
</tr>
</tbody>
</table>

<h2>Output</h2>

<table>
<thead>
<tr>
<th>origin</th>
<th>destination</th>
<th>route_frequency</th>
<th>avg_duration_minutes</th>
</tr>
</thead>

<tbody>
<tr>
<td>JFK</td>
<td>LAX</td>
<td>2</td>
<td>210</td>
</tr>

<tr>
<td>JFK</td>
<td>ORD</td>
<td>2</td>
<td>103</td>
</tr>

<tr>
<td>JFK</td>
<td>MIA</td>
<td>2</td>
<td>172</td>
</tr>

<tr>
<td>LAX</td>
<td>SFO</td>
<td>2</td>
<td>82</td>
</tr>

<tr>
<td>LAX</td>
<td>SEA</td>
<td>2</td>
<td>157</td>
</tr>
</tbody>
</table>
Explanation:

From each origin (JFK, LAX), the query returns the top 5 most frequent destination routes. Since each origin has only two routes in this dataset, they are all included. For routes with the same frequency, sorting is done by increasing average duration.

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

Cubic Corporation Interview Questions

Cubic Corporation Interview Guides

Cubic Corporation Interview Questions

Challenge

Discussion & Interview Experiences

Discussion & Interview Experiences