Clean and Vegan Skincare Trends at Sephora

Avatar
Posted on May 16, 2020

Recently, while browsing Sephora’s website, I noticed two new categories of skincare products featured: vegan and clean. It looks to be a growing movement nowadays, where people are becoming more conscious of their everyday purchases, and that includes their skincare. I was curious to look into this trend, and see if I could gather any insights. For my project, I used Selenium to scrape Sephora. You can find my work on Github

First off, some quick definitions:

Clean – means a product is “formulated without a list of over 50 ingredients, including sulfates (SLS and SLES), parabens, phthalates, and more” – as defined on Sephora’s websites. 

Vegan – means that a product does not contain any animal products or by products.

Conventional – for the sake of simplicity I will refer to products that are neither vegan nor clean as conventional skincare products.

Currently Sephora offers 947 clean skincare products, and 843 vegan products. However, conventional products still outnumber the sum of vegan and clean skincare options combined. Clean and vegan skincare products have the largest presence in moisturizers and treatments, while there is still a lot of opportunity for growth when it comes to cleansers, eye care, lip products, and sun protection. 

Next, I wanted to compare the prices between the different product types to see if clean and vegan products are priced higher. Looking at the distribution of prices, there doesn’t seem to be any clear trend if one product type outprices the others. Contrary to what I had previously thought, sometimes vegan and clean products can be cheaper than their conventional counterparts. The large outliers are explained by certain brands being more expensive. For example: La Mer (a brand with only conventional options) is focused on luxury skincare, therefore their products will be more expensive.

With this in mind, I wanted to look into whether or not brands are pricing their vegan, and/or clean products more. On the left I compare the average price difference brands charge for their vegan vs non-vegan products, and on the right I compare the difference in price that brands charge for their clean vs non-clean products to determine if there is any existence of a surcharge for labeling products as vegan, and clean, respectively. In general, it looks like brands do charge more for their vegan, and clean options, indicating a financial opportunity to offer these types of products to customers.

One feature on Sephora’s website that caught my eye is the "number of loves", which quantifies how many times a product has been saved by a user. What’s interesting is that despite conventional products outweighing the number of products offered, the combination of vegan and clean products outnumber conventional products in the number of loves received. This indicates that these products are gaining a considerable amount of interest from Sephora's customers. 

Number of loves is important, because it is correlated with how many reviews a product receives. More reviews boost a products visibility on Sephora’s site, and indicates that more people are actually purchasing the product. I fitted a simple regression line with a slope of .016. This relationship is statistically significant with a p-value .019. We can interpret this as an extra 16 reviews for every additional 1000 number of loves on a product. This linear relationship is critical for vegan and clean brand marketing, in contrast to the most popular conventional skincare brands which already have established customer loyalty. It's worth it for vegan and clean focused businesses to invest in a marketing strategy that can effectively boost their sales, by focusing on increased visibility and increased customer interest/attention.

Finally, I wanted to look at how rating relates to the price. There is no visible linear relationship, indicating that customers are more interested in the quality of the product, over the price, and that Sephora customers are willing to pay extra for a product that works well.

In conclusion, with consumer consciousness on the rise, clean and vegan-friendly skincare is here to stay. This is a great financial opportunity for skincare businesses to offer more of these products to meet customer demand. ​Even with so many options currently catering to this part of the market, there are still many opportunities for growth. Perhaps we'll be seeing more high quality clean sun protection, and vegan lip products from Sephora in the near future.

Future work:

  • I am interested in seeing if certain demographics prefer a particular product type. For example: those with dry skin may prefer clean products due to being sensitive to irritants, while vegan skincare products might be more popular with younger populations. I would need to scrape each product's reviews in order to verify my hypotheses. Due to the speed limit of Selenium, I will investigate other methodologies of scraping such as using an API.

About Author

Avatar

Jessie Wang

Jessie is a graduate from the University of California, Santa Barbara with a degree in Actuarial Science. Upon graduation, she joined UnitedHealth Group as an actuary where she gained a wide array of experience in the healthcare industry....
View all posts by Jessie Wang >

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