How should improve profit through private label

Lanqing Yang
Posted on Feb 16, 2020


Pet online retail is a growing industry,  people who take responsibility to take care of a pet many end up seeing pets as their own families. Among the pet online retailers, is one of the most popular ones and it is owned by PetSmart. Chewy reported $3.5 billion in sales for fiscal 2018, up from $2.1 billion in 2017.

However, one the same time, more and more competitors join in this promising market, such as Amazon. In order to achieve profitability, started its private-label - American Journey, and they try to increase the private label sale from 5% to 15%. To help the company achieve this objective, this project will analyze's private label's performance.

The questions this project wants to answer are: How does private-label perform comparing to other brands? And how to improve the private label's popularity and rating?

Web Scraping:

For this project, my focus is on cat food. Before analyzation, the first step is to gather all the information that may give us insights. The method I used is Scrapy because of its efficiency. Below are data I chose to scrap, they are: Brand, Product Name, Price, Number of Reviews.

Besides the general information, I also want to be able to evaluate the product through its nutrition, product type, and weight. Thus, I also scraped the Key Benefit, Product Description ( life stage, weight, food form, food texture, special diet, etc.). 

Besides the product description information, Reviews are important data. Thus, I scraped individual Reviews, Reviews  

Brand Analysis:


My approach to understanding the private label's current state is to first check its Popularity. I measure the popularity by the total number of reviews each brand receives. From the chart below, we can see that American Journey's popularity is among the top 10. My future analyzations are also conducted within the scope of the top 10 brands.

Product Availability:

Then, I evaluate the product availability, which is how many products each brand has and available on From the graph, we can identify that, among the top 10 popular brands, American Journey has the least product types. Most popular brands have more than 50 different products, but American Journey only has 20 products available.


Then, I want to evaluate the brand's reputation. The way to measure it is though the average rating for each brand. Although, all the top 10 popular brands receive higher than 4.0 average ratings. American Journey shows the worst performance. 

Rating over Years:

To further investigate how American Journey's ratings change over months and years comparing to other top brands, I conducted a simple time series analysis. From the graph below, I compared the American Journey to the Top 3 highest rating brands. American Journey's rating fluctuate a lot and shows an overall declining trend, and other brands' ratings are more stable. 

Demand over Years:

In order to gain profits, it is important to increase the demands of the products. From the graph below, Fancy Feast shows a significant increase in demand, while other brands', including the private label's demands, didn't change much. 

The current state is that although American Journey is within the top 10 popular brands, it doesn't show advantages on product availability. Also, American Journey might want to take more effort into maintaining their ratings. The next step is to analyze how to increase private label's reputation and popularity.

Does Price Affects Ratings?

Since we have identified that Chewy's private label didn't maintain their ratings very well. One question to ask is whether the price is the factor that affects the rating. The graph below shows the relationship between the unit price ( by pounds ) and the average rating, and it doesn't show a clear relationship. 

American Journey's product unit price is the same as the Fancy Feast, but its rating is relatively low. There is also a brand like Royal Chain Veterinary Diet that has a higher unit price, but the highest rating score. The only case that high price results low rating can be seen from brand Wellness. 

From the scatter plot below, we can clearly see that there is no strong relationship between average rating and unit price. 

Since Price is not necessarily the factor that affects ratings, we can conclude that the pet owners who shop on are not price sensitive. They do not prefer one brand simply for its cheap price since they also like some more expensive brands such as Royal Cain Veterinary. Then, is there some other qualities they look for? 

If Not Price, What Else?

The chart below compares American Journey with Royal Cain Veterinary and Fancy Feast, the top two performers. Royal Canin Veterinary is more expensive than the other two brands, but it also has the most types of special diets to fulfill various cats' health demands.  Fancy Feast is among the same price range as American Journey, and it also has a couple of special diets. American Journey, however, has only two types of special diets. 

Many cat owners now are not price-sensitive, they look for a better quality of food for their cats. Different cats may have different health concerns and needs. Since is seeking a path to profitability through a private label, to improve the cat food product line, they could create a more diverse and nutritional product offering.

Key Ingredient:

Through natural language processing, I also found that it could be beneficial for American Journey to highlight ingredients such as high-protein, vitamin, and omega to effectively attract customers. The chart below visualizes the top ingredients that are highlighted on high rating products.

Future Improvements:

  • Since I also scraped all the customers' reviews, it would be beneficial to further conduct sentiment analysis. 
  • In the future, I can also utilize the information about cat food taste, life-stage to conduct a more comprehensive analysis. 

About Author

Lanqing Yang

Lanqing Yang

Lanqing graduated from Fordham University with a bachelor's degree in New Media and Digital Design. She is currently pursuing a master's degree in the quantitative field to further strengthen her knowledge and skills. Through her problem-solving experience as...
View all posts by Lanqing Yang >

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws 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 Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R 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 Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp