Takehomes

Determine the percentage of customers that won't wait for an item to get restocked.

Probability
Time Series
Python
6 Hrs

Answer multiple questions to show your data science skills

AB Testing
SQL
Machine Learning
Growth
Analytics
6 Hrs

Create a model to predict how long it will take a driver to deliver an order

Regression
Python
Machine Learning
5 Hrs 30 Mins

Create a model to recommend bookings to Brazilian Airbnb users

Recommendation Engine
Machine Learning
72 Hrs

Help a cross-functional Airbnb team grow bookings in Rio de Janeiro

Growth
EDA
Data Visualization
Presentation
Analytics
6 Hrs

Formulate business goals related to driver churn

R
Business Case
Pandas
1 Hr

Determine how well a product at Stripe is performing.

Marketing Analytics
EDA
Analytics
6 Hrs

Preform Open-ended analysis of a data set and make a notebook showing any interesting threads you find

Business Case
EDA
Analytics
3 Hrs

Bike-Sharing Program Q&A

Mckinsey & CompanyMckinsey & Company

Answer questions regarding data from a bike-sharing program.

EDA
6 Hrs

Conduct analysis to discover how to promote Affirm to merchants

SQL
EDA
Presentation
6 Hrs

Create a model to forecast revenue from sales in the future

Time Series
Regression
Pandas
Python
Machine Learning
6 Hrs

Create forecast the revenue of new movies

Regression
Pandas
Python
Machine Learning
6 Hrs

Create a model to predict if an article is spam or not

Pandas
Python
Classification
Machine Learning
6 Hrs

Estimate the financial impact of launching a new product line on monthly sales.

Marketing Analytics
Business Case
Growth
Presentation
Analytics
4 Hrs

Answer multiple questions to show your data science skills

3 Hrs

Design and write queries for a KPI dashboard

Database Design
Data Engineering
SQL
6 Hrs

Determine if a newly launched product effectively reduces overspending (and answer some probability questions).

Probability
AB Testing
Growth
EDA
6 Hrs

Create a model to determine if a promotion should be given to a user

6 Hrs 30 Mins

Create a model to classify if a piece of text was made a human or a bot.

NLP
Python
Classification
Machine Learning
6 Hrs

Find what state Grubhub should focus on for new product development

Marketing Analytics
Business Case
EDA
Analytics
3 Hrs

Complete four short data science questions covering the full breath of the job

AB Testing
ML System Design
R
Marketing Analytics
Business Case
Python
Machine Learning
Analytics
1 Hr

Create a model to predict the frequency of high winds that can help estimate how long it takes trucks to flip over in high winds

Python
6 Hrs

Determine the most efficient use of space inside a supermarket.

2 Hrs

Create a model to price daily estimate the shelf value of different food items

Machine Learning
6 Hrs

Create a model to predict whether or not a debtor will default on a loan

6 Hrs

Design a system to show the correlation between the price of a cryptocurrency and Twitter sentiment about the token.

Finance
Feature Design
Data Engineering
6 Hrs

How would you build a product recommendation system?

Deployment
Data Cleaning
Recommendation Engine
5 Hrs

Explore, analyze, visualize, and model Supercell's revenue data

Machine Learning
EDA
Data Visualization
Analytics
6 Hrs

Write a script to transform the provided CSV to a desired output CSV.

Data Cleaning
Python
2 Hrs

Complete two long-form challenges, to test your SQL and story telling skills

SQL
Business Case
Analytics
6 Hrs

Build a model that predicts the type of crime as soon as an emergency call comes in.

ML System Design
Classification
Machine Learning
5 Hrs

Analyze the business prospects for a new e-commerce startup and see if they are worth investing in

Marketing Analytics
Business Case
Time Series
Regression
Pandas
Python
EDA
Analytics
6 Hrs

Do exploratory data analysis on user behavior on Gordon Ramsay Masterclass page

3 Hrs 30 Mins

Pitch Forecast

Swish AnalyticsSwish Analytics

Build a model that will predict the probability of a fastball, slider, etc., in a real-time environment.

Deployment
ML System Design
Classification
Machine Learning
4 Hrs

Create a model to cluster inquires by their text content

4 Hrs

Create a model that predicts the overall title risk of a property.

Regression
Python
Machine Learning
6 Hrs

Create a model to detect if a transaction on a credit card was fraudulent or not

Python
Classification
Machine Learning
6 Hrs

Given some legacy Python 2 code, identify bugs and errors in the code, reformat the code to Python 3, and suggest other ways to improve the code.

Code Review
Model Evaluation
Python
Machine Learning
2 Hrs

Build a transparent Redis proxy service

Web Development
Python
6 Hrs

Mortality Rate during Sha'ban

Saudi commission for health specialtiesSaudi commission for health specialties

Conduct analysis to see whether or not more people die during the month of Sha'ban.

R
Python
EDA
72 Hrs

Loan Default Model

Business opticsBusiness optics

Create a model to predict the probability of a debtor defaulting on a loan

Pandas
Python
Classification
Machine Learning
3 Hrs

Give a presentation to help the product and engineering team understand user behavior.

Marketing Analytics
Presentation
Analytics
6 Hrs

Create a model predict if a permit is about electrical permissions

Python
Classification
Machine Learning
6 Hrs

Create a presentation with suggestions on how to reduce traffic congestion

Deployment
Machine Learning
EDA
Presentation
72 Hrs

Create a function to parse messy json files

Data Cleaning
Data Modeling
Algorithms
45 Mins

Create a model to predict if a user will click on a link

5 Hrs 30 Mins

Write two queries using different approaches to aggregate NPS by client by month.

SQL
6 Hrs

Identify which features are most important for getting a user to adopt our product

Analytics
12 Hrs

Perform analysis and modeling to access the risk of cyber attacks on healthcare facilities

Statistics
Machine Learning
EDA
6 Hrs 30 Mins

Perform analysis on a data set of product details that is formatted in an inconvenient manner. Provide suggestions to improve the data model.

Data Cleaning
Business Model
Business Case
Analytics
2 Hrs

Create a model to price daily electricity costs for households

Time Series
Regression
Pandas
Python
Machine Learning
6 Hrs

Discharge Rate vs. Workload

Mid-atlantic permanente medical groupMid-atlantic permanente medical group

Determine if the amount of "busy days" at a hospital affects the discharge rate of a patient.

Python
EDA
Presentation
6 Hrs

Analyze which pricing method is best for e-learning course

Marketing Analytics
Analytics
5 Hrs 30 Mins

Create a model to estimate the acceleration of a car

Deep Learning
Time Series
Regression
Pandas
Python
Machine Learning
6 Hrs

Evaluate conversion rate predictions by device for a set of entities.

Model Evaluation
Machine Learning
6 Hrs

Create tables that grouped by a complicated key

Pandas
2 Hrs

Conduct analysis the prices of short-term rentals in Phoenix, Arizona

Business Case
Pandas
Analytics
3 Hrs 20 Mins

Answer multiple questions to show your data science skills

Multiple Questions
Probability
SQL
6 Hrs

Complete two short data science questions covering the EDA and Error Analysis

Statistics
Pandas
EDA
Analytics
1 Hr 30 Mins

Give a recommendation on how City Year should focus on different types of clients based on survey data.

Probability
Business Case
6 Hrs

Answer questions about two data sets that have an usual way of labeling data

Pandas
Python
EDA
6 Hrs

How would you allocate the budget you were given to acquire new users?

Marketing Analytics
Growth
EDA
6 Hrs

Build a model to predict the number of order requests per hour for five regions.

Python
Machine Learning
6 Hrs

Create a model to predict if a book-delivery startup will be able to pay back a loan

Pandas
Python
Classification
Machine Learning
6 Hrs

Create a model that predicts if a child will likely play Square Panda games in the next seven days.

Marketing Analytics
Machine Learning
6 Hrs