Zappos Web Scraping: In Shoes We Trust

Ali
Posted on Feb 8, 2021

Shoes are an important component of our outfit and may say a lot about the wearer’s personality, it’s interesting that there are scientific studies [1] to support this hypothesis that people can be judged by their shoes! The global footwear market is a multi-billion U.S. dollar industry. The United States has the largest footwear market in the world, amounting to approximately 20.9 billion U.S. dollars in revenue in online shoe sales with 11.3% of annual growth between 2015 and 2020 [2].

Zappos.com is one of the most popular online shoe retailer because it provides excellent all-round service while offering a good range of shoes at competitive prices. The website itself is easy to navigate, has excellent product photography, and offers loads of useful information on each product page. Zappos is based in Las Vegas, Nevada, and was founded in 1999 by Nick Swinmurn and launched under the domain name Shoesite.com. In July 2009, Amazon acquired Zappos in an all-stock deal worth around $1.2 billion at the time. They started from $1.6 million in gross sales in 2000 and reached the as Forbes reported produced in excess of $2 billion in revenues in 2015 [3].

For this study, I have scraped more than 13000 pairs of men’s shoes from Zappos in six main categories of sandals, loafers, boots, sneakers, oxfords, and running shoes. For each pair of shoes, I have scraped brand, model, price, rating (0-5), number of reviews, true to size score (0-100), true to width score (0-100). Among these categories, boots have the highest median price, and sandals have the lowest which was aligned with what I was expected. Boots also have the highest pair of shoes in their category which is $775 from La Sportiva. In terms of average fit score (which is the average of true to size and true to width for each pair), Sandals have the highest median score, and loafers have the lowest. I was expecting to see the more casual/comfortable shoes to have higher scores than more formal/work shoes like oxfords and boots which is the case with the exception of loafers.

In the next step, I was curious to see how the brands perform in each category in terms of pricing, fit score, and average customer rating. to have a more accurate analysis especially for average customer rating, I only picked the brands that had at least 10 models and each of those models had more than 10 reviews and plotted the top and bottom three brands (with the ties) for each variable in each category.

In the sandals category, the people who bought Mephisto were very happy although they paid a fortune for a pair of sandals and also didn’t get the best fit in the category. For Dr. Martens, their poor fit cost them the customer rating and for New Balance, even the low price and high score fit couldn’t make their customers happy.  

In the boots category, none of the least expensive brands were able to satisfy their customers and obtain high ratings. It’s also shown that Under Armor’s effort to make a better fit paid off and put them in the top 3 highest rating brands.

In the loafers category, Bruno Magli may charge you a lot but based on the customer rating, the folks who bought it, believe that it worth the money you pay. On the other hand, I was really upset to see Allen Edmonds which is one of my personal favorites isn’t the most popular among its customers. I have to admit that they don’t make the best fit and it gets even worse when you know that they are also very pricy!

It seems that in running shoes’ world SKETCHERS didn’t leave much to say. They have the best fit, are one of the least expensive brands in the category and they have the highest customer ratings! It was a surprise for me not to see ASICS in higher rating brands since I always thought they are the king of running shoes!

The other interesting analysis that can be done with the scraped data is the variety of models offered by each brand and their price distribution. For example for oxford shoes, Clarks offers the most variety with 133 different models (top 10 brands with the most varieties of models are shown) and they have been reasonably priced around $100. The data also shows that Dockers has the most consistent pricing among their models while Magnanni and Cole Haan and ECCO have more dispersed pricing for their different models.

The data which has been scraped during this project can be useful for those who are in the online retail of men’s shoes or who are planning to get into this business. The data can provide some insights into the popularity of different brands in various shoe categories, their prices, and their fit score.

  • As an online shoe retailer, you can pick only the most popular brands if you prioritize saving the warehouse space over offering more variety of products.
  • Price distribution of different brands and the number of models that each brand offers can provide some estimation on how much you may need to invest in your inventory.
  • The fit score of the different brands can also be very useful to estimate what would be your return rate since a lower fit score reduces the chance of getting the right shoe by the first online purchase and a high return rate may affect your operations if it’s not planned beforehand.

Github

Reference

[1] Shoes as a source of first impressions

[2] IBISWorld

[3] Zappos

About Author

Related Articles

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