Data Analysis on Protein Powers in Vitamin Shoppe

Posted on Feb 21, 2021
The skills I demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.



According to data from Fortune Business Insights, the “global dietary supplement market was valued at USD 48.22 billion in 2019 and is projected to reach USD 117.92 billion by 2027”. This massive market is continuing to grow in popularity as people are constantly bombarded with fad-diets and swimsuit cover bodies.

However, there is room for danger as much of this market is not regulated by the FDA. Companies have a good amount of freedom in their ingredients, marketing, pricing, etc. The general public has little idea of what they're putting in their bodies when they buy these products. Most of their rationale is based on readily available data such as reviews, recommendations, and pricing. For this reason, I conducted a type based analysis of different protein powders offered on to provide a more detailed picture  of how customers choose their products.

The Scrape

To obtain this data, I scraped Vitamin Shoppe’s protein powder subcategories using selenium. The scraper opened each product’s URL and scraped the necessary information including product name, item number, listed price, price per serving, brand, rating, number of reviews, and the number of people who recommended yes or no.

Types of Protein Powder

The website’s protein powder section was divided into 5 categories: Whey Protein, Casein Protein, Natural Protein, Plant Based Protein, and Other Protein. For those unfamiliar with the extensive variety, they are marketed as the following:

  • Whey protein, a milk product, is a good choice for a workout because it is easily digested and absorbed which can help you feel full and energized
  • Casein, also a milk product, is absorbed more slowly so that you can feel full longer and it can aid in long term muscle growth
  • Plant-based protein can be made from various plant proteins including beans, rice, pea, and hemp. Essentially, the benefits come from whatever its plant source is. This is an ideal option for people who are intolerant to milk products or vegan
  • Natural proteins on this site included anything considered organic, containing natural ingredients, non GMO, etc. 
  • Other Proteins include blends of different proteins for example, a Whey and Casein protein blend, or products that did not fit into the other subcategories

Data Visualization

Analyzing the overall market of the protein powders offered at Vitamin Shoppe, I made a scatterplot comparing the listed price to the number of reviews for that product. The red dashed line indicates the mean price for all the protein powders offered. The observations seem to be normally distributed around the mean showing that most consumers pay the average price for their proteins. Not as many people are willing to pay other prices.

Data Analysis on Protein Powers in Vitamin Shoppe

Data Analysis on the Different Types

To get a better idea of differences in the types of proteins offered, I made a box plot of the type of product compared to the listed price of each type and put that alongside another box plot of the type of product compared to the price per serving of the powder. Interestingly, if you just looked at the distribution of the listed prices, one would conclude that whey proteins generally contain the most expensive products and plant based/natural are on the lower end. This is not what you would expect as natural products are assumed to be more expensive.

However this assumption is proved correct as you examine the boxplot of price per serving distribution. Here, whey proteins have the lowest price point. Whey proteins may have higher listed prices, but they make more sense economically if someone is using this product every day. The plant based and natural may seem cheaper but may just be offered in smaller quantities.

Data Analysis on Protein Powers in Vitamin Shoppe

Distribution of Ratings

To visualize the distribution of ratings awarded by customers to products of each category, I created a stacked histogram. This makes it easy to see what ratings each type of protein has received.

Data Analysis on Protein Powers in Vitamin Shoppe

Additionally, the website offers customers who purchased a product the ability to select whether they recommend it yes or no. I created another set of boxplots to visualize the number of people who selected yes or no for products in each subcategory. The left boxplot, people who recommended yes shows pretty tenuous results. However, it is more telling to look at the right plot where people returned to the website and recommended no.

For the plant based section a good amount of people said they would not recommend this product for a range of plant based products. In many cases, a consumer is more likely to take a negative review into consideration and be persuaded to not purchase the product.

Lastly, I constructed a series of bar charts to examine which brands are selling these specialty types of proteins. The five brands with the top counts of each type of protein is shown below. This can be cross referenced with the subsequent bar chart which displays the top 10 protein powder brands that received the highest ratings across all types. Such analysis ensures that the product you are purchasing is of the best quality.

Future work: 

  • Explore consumer data on other sites that offer these protein powders to normalize the rating data and be able to find the best products within these type categories
  • Ingredient analysis of different protein products and cross reference with the FDA’s list of chemicals to look out for in protein products to see how many of these products contain harmful ingredients


Data Resources:



About Author

Jessica Joy

Recent graduate from Binghamton University with a Bachelor of Science in Financial Economics. Highly motivated problem solver seeking opportunities to leverage data wrangling and analysis skills to provide key insights in real-world business problems.
View all posts by Jessica Joy >

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