Now reading:
[Case Study]: How did the sales of an online cosmetics store increase thanks to the product recommendation system?

[Case Study]: How did the sales of an online cosmetics store increase thanks to the product recommendation system?

Avatar Zuzanna Pajorska
31 sierpnia 2021
clock icon 6 min
Image

Can the recommendation system help you recover the conversion on the inaccessible product page? Dawid Skwiot, director of the British online cosmetics storeRoxie Cosmetics, approached us with this question.

The case study of the implementation of our Recostream engine in this online store shows that not only is it possible, but also clearly affects the increase in sales throughout the store. See an example of the application of recommendations in Roxie and find out what the latest few months of our cooperation looked like.


Implementation of the product recommendation engine in the Roxie online cosmetics store in a nutshell:

results of the implementation of recommendation system in online store

Would you like to know more application examples? Click on the link to read the Case Study of the implementation of the recommendation engine in a women's clothing store.

About the store

Roxie Cosmetics UK Beauty Store is an English online cosmetics store with natural and vegan cosmetics. In the catalog you can find a wide range of hair, body and skin care products, makeup, nails and accessories necessary in a home SPA.

  • Platforma: Shopify
  • Number of products: approx. 11 000
  • Store address: www.roxiecosmetics.co.uk
  • Deployment configuration: February 2021

About Recostream

We are developing an AI recommendation system that allows you to increase sales by 5-10%, while allowing store customers to find products that interest them faster and more accurately.

Placing recommendations is possible in a few minutes without the participation of programmers and their effectiveness is optimized by artificial intelligence algorithms and machine learning based on the actual customer behavior.





Purpose of the implementation

As we mentioned at the beginning of the Recommendation Case Study, the owner of the online cosmetic store Roxie Cosmetics approached us with a specific problem that our recommendation system had a chance to solve.

After discussing the operation of the recommendation system and pointing other benefits that can be achieved after installing our system, we developed an implementation plan to help solve the following issues:

  • Recovery of conversions on pages of unavailable products
  • Increase in the value of the shopping cart
  • Reduction of abandoned shopping carts
  • Improved CTR
  • Increasing Conversion

Results after implementation

For the past six months, we have been constantly analyzing and observing the actual impact of our algorithm on sales in the Roxie online store. At the very beginning of our cooperation, the store was integrated with Google Analytics using the Enhanced Ecommerce option.

As a result, information on all user interactions with recommendation banners on the store's website was collected in the form of GA events.

The results after implementation are as follows:

results of implementation of recommender system

The most profitable recommendation locations:

One of the most important initial decisions was where to put recommendations on the store page. Ultimately, we decided to place banners with product recommendations in five key places on the store's website in the web and mobile versions.

Each location brought different results and the best converting recommendations depending on the location were arranged in the order of the most effective:

  • Product page
  • Shopping cart page
  • Pop-up on the page of an unavailable product
  • Dynamic recommendations on the blog page
  • Homepage

Implemented solutions

Another, equally important point was to determine which recommendation model to implement in an online cosmetics store. Recostream has several types of product recommendations that differ depending on what the client wants to achieve.

The owner of the Roxie store has decided to buy as many as 10 of the following models:

  • Bestsellers in Store
  • Cross Sell
  • Most Similar in Category
  • AI Maximized Conversion
  • Most Similar in Store
  • Most Viewed in Category
  • Others Also Added to Cart in Store
  • Others Also Viewed in Store
  • Rule-Driven Recommendations
  • Recenelty Visited in Store
product recommendations
Recommendation model: Recently Visited in Store. Location: shopping cart page


product recommendations
Recommendation model: Bestsellers in Store. Location: homepage


product recommendations
Recommendation models: Similar, Most viewed in the category, Cross Sell. Location: pop-up on an unavailable product page


product recommendations
Recommendation models: Others also bought, Others also added to the cart. Location: product page


product recommendations
Recommendation models: contextual recommendations. Location: blog


product recommendations
Recommendation models: The most popular. Location: homepage (mobile version)



Installation process

How was the recommendation engine installed in the Roxie Cosmetics store? There were no surprises here - the integration of the store set up on the Shopify platform with the recommendation system took a few minutes and the configuration on the technical side of the Recostream team took one working day.

The entire implementation process looked like this:

  1. Registration on the recostream.com website, where the email address and the URL of the store were provided.
  2. Lines of JavaScript code have been pasted into the shop's website. It took 3 minutes without any programmer assistance.
  3. The Recostream team made a configuration of the appearance and adapted it to the design of the store.
  4. The AI recommendation engine was launched in one business day.
  5. Trial period started: 30 days.
  6. The results were integrated with the Google Analytics account for independent and objective performance evaluation.
  7. Ongoing contact with the customer service manager was maintained.



Client about us

The Recostream recommendation system stands out because of the fact that it has algorithms that have a real impact on sales and the effectiveness of which can be objectively and independently assessed.

In addition, we made use of the possibility to recover conversions from unavailable products, which was very successful in our online cosmetics store and translated into increased sales.

I am satisfied with the cooperation with Recostream so much that I decided to implement the system in my other store.

Dawid Skwiot
Director of Roxie Cosmetics LTD

Are you curious about the implementation of the Recostream recommendation system in a furniture store? See another Case Study!

We would like to invite you to take advantage of the 30-day trial period!

Register and install the AI / ML recommendation engine in 3 minutes without the help of an IT specialist. We will take care of the rest.

If you have any questions, please contact team@recostream.com

You can read more about the recommendation engine on our blog.


Case study summary of the implementation of the recommendation


The implementation of the product recommendation system for a British cosmetics store has taught us what needs the customers of Roxie Cosmetics have and what solutions bring the best results and translate into increased sales.

In the Case Study of the implementation of recommendations, we discussed the entire process - from the installation of JS code on the store's website, through the implementation of as many as 10 types of recommendations in various store locations, to discussing the effectiveness measured on an ongoing basis through Google Analytics.

We are happy to work with Roxie Cosmetics and we are looking forward to the effects of the next one in Mr Skwiot's other store.

arrow-up icon