Using Data to Analyze Starbuck's Country Selection

Posted on Nov 9, 2020

Starbucks is one of the world's most famous coffee franchises. They are very well-established in North America, but they also have a big presence abroad as well. As of 2017, Starbucks had at least one store in at least 254 different countries and territories. When Starbucks is trying to decide which country to expand to, what are some important features in such a country? 

Here were the top ten countries in the world with the most Starbucks stores:

1. United States of America 13608
2. People's Republic of China 2734
3. Canada 1468
4. Japan 1237
5. Republic of Korea 993
6. United Kingdom of Great Britain and Northern Ireland 901
7. Republic of Turkey 652
8. United Mexican States 579
9. Taiwan 394
10. Republic of the Philippines 298

When examining this list, a few things stood out to me:

  • There are quite a few Asian countries in the top ten. This was very surprising to me because I did not know that Asia had such a prolific coffee culture until I began doing this research. I know that historically, tea has been a choice beverage for Asian countries, so I imagine this has something to do with why coffee is so popular in Asia.
  • Canada is a bit of a surprise to me as well. I have been to Canada quite a few times now and I know that Tim Hortons is a big hit. In my mind, I would have thought that Starbucks would steer clear of Canada, seeing that they would have very stiff competition with Tim Hortons. It seems as if Starbucks believed that they could compete with Tim Hortons and so they had no problem investing heavily in Canada.
  • Having Mexico in the top ten makes sense to me because I am aware that Latin American countries are very big producers of coffee beans.

Why are these the top ten countries? What is it about countries like these that make them so attractive to Starbucks? Is Starbucks attracted to countries that already have a well-established hot-drink culture? WHy do Asian countries dominate the top ten? 

In order to try to discover the answer, I decided to look at some basic statistics about countries to try to decipher if there was any correlation between these basic features and the number of Starbucks stores in the said country. The features I considered are:

  1. Gross Domestic Product (GDP)
  2. Population
  3. GDP per capita
  4. Illiteracy rate
  5. Crime rate
  6. Median Household Income
  7. Median Income per Capita

I selected these features because I believe they are fundamental to any country and that they would help a business to have metrics to help them know if the said country would have an interest in their business. For example, if you want to sell luxury sport cars, you probably wouldn't build the headquarters of your business in a country with a very low GDP (per capita). If you wanted to open a book store in a foreign country, you might think twice before opening it in a country with very low illiteracy rates. In the case of Starbucks, they are one of the higher-end coffee franchises, so they would probably care about the above features because it would give them a good idea about whether or not the country in question would be properly suited for their investment.

I gathered data on these features from the year 2016 because the data I have on Starbucks is from 2017. All told, I had 8 different datasets, one for each feature and one for the store count of each country. I used a programming language called R, to do some data manipulation and analysis. The packages I used the most are called dplyr, ggplot2, and Hmisc. Dplyr is a very good package for data manipulation, ggplot2 is great for data visualization, and Hmisc is great for statistical analysis.

How would I use these features to find out which were important (if any) for understanding the choices Starbucks made in regards to which countries they would invest in the most? I decided to examine the correlation coefficients of each pair of features in the dataset. Here is what I found:

There was a 0.91 pearson correlation between Store Count and GDP. This means that there is a strong linear relationship between these two features. In other words, as GDP increases, store count increases. Notice that the USA and China are numbers 1 and two respectively on the top-ten list. This is what got me thinking about GDP as being an important feature in the project.

The United States is an outlier here, but even if you take the USA out, there is still fairly strong linear relationship present.

Using the Population and Store Count features, I performed some simple feature engineering by creating a Stores per Capita feature. I generated this new feature by the following formula:

Stores per Capita = Store Count / Population

What this helped me to find was that Stores per Capita and Median Household Income had a pearson correlation coefficient of 0.81. This shows that these two features have a strong, positive linear relationship. In other words, as Median Household Income increases, Store Count increases.


From the correlation matrix, I was able to find another strong linear relationship between Stores per Capita and Median per Capita Income. The pearson correlation coefficient between these two features was 0.63. 


In conclusion, it seems that economics played a huge factor in this analysis. This makes sense because Starbucks is a high-end coffee franchise. They do not sell the cheapest coffee, so one would expect Starbucks to want to expand in countries where the citizens make enough money to afford the products. In addition to this, Starbucks chose to invest heavily in countries that already had a well-established hot-drink culture. This completed my analysis. I hope you had as much reading this as I did writing it. Next time you walk into a Starbucks, remember to think about what you just read.

The skills I demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

About Author

Mark Carthon

Data Scientist with 7+ years of work experience and a strong mathematical background. Passionate about applications of Machine Learning and Deep Learning in industry.
View all posts by Mark Carthon >

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI