<img height="1" width="1" style="display:none" src="https://q.quora.com/_/ad/ad9bc6b5b2de42fb9d7cd993ebb80066/pixel?tag=ViewContent&amp;noscript=1">
Vector (43)CASE STUDY — ADVANCED CATEGORY NAVIGATION

Leading sports retailer in Europe increase revenue with 12% with Loop54 Advanced Category Navigation

DOWNLOAD CASE STUDY PDF

SPORT

“We had a challenge with our product listing pages not yielding robust conversion gains at XXL after some A/B-test. So the product team had workshops, set up hypotheses, implemented them with the new Loop54 AI engine GAS, tested extensively and proved fantastic conversion gains (60 x ROI). With the project management from Customer Success the XXL team became very satisfied and decided to use Loop54 for category listings within days of the test being finished”.

Robin Mellstrand
Loop54 CEO

About XXL

XXL’s vision is to be the preferred sports and outdoor destination in Europe. Since the inception in 2001, XXL has built a sports retailer with an annual turnover of approximately NOK 10 billion. Today XXL has 90 stores in Norway, Sweden, Finland and Austria. It is also the largest online sports retailer in the Nordics.

In total, XXL has more than 5.000 enthusiastic employees. XXL provides its customers with a unique mix of great brands, great expertise, great assortment, great accessibility and great prices.

Background to Navigation project

Loop54 continuously works with our customers to improve on-site search and navigation. For our sports and outdoor customer XXL, we suggested testing the Loop54 advanced category navigation against their current navigation solution based on Apache Solr. What we wanted to do was increase conversion and revenue from visitors using navigation as an alternative for search when browsing on-site. XXL already uses Loop54 search and personalisation since 2015.

XXL decided to do an A/B/C/D test with different variants of the Loop54 engine setup based on business logic using personalisation, boost and bury, commonly popular products, customer behaviour and customer purchases compared to XXLs existing solution.

XXL implemented their frontend for the navigation to call the Loop54 API with XXLs product catalogue.

Pic (1)

The hypothesis of how people want to navigate in categories

The Loop54 product team had workshops and set up hypotheses about how people wanted to navigate on an e-commerce site using category navigation. As a result, 3 different variants were implemented on the XXL environment using the new Loop54 AI engine GAS.

For the A/B/C/D test Loop54 configured 3 different engine setups for the category listings. All engine setups included personalisation from Loop54.

A - Hypothesis - Chaos

The hypothesis is based on the assumption that the user is going to a category listing and then using facets to make their scope narrower. In this case, instead of creating a structured grouping of products, we wanted to maximize the exposure of different product types high up in the listing to create a sense of what type of products are under the category. This means that we will generate a larger mix of products - so the brand would in this case have given a mix of trousers, jackets and boots at the top of the results.

The results

I
+

0

%

Average Order Value

I (1)
+

0

%

Average Session Value

I (2)
+

0

%

Average Price

I (3)
+

0

%

Revenue Increase

Pic (2)

B - Hypothesis - Lightweight Lucy

To have a reference to compare with, we tested a stripped-down category listing that is largely based on a linear combination of local popularity (depending on the selected category listing), global popularity (the popularity of products in general) and boost & bury rules.

The results

I
+

0

%

Average Order Value

I (1)
+

0

%

Average Session Value

I (2)
+

0

%

Average Price

I (3)
+

0

%

Revenue Increase

C - Hypothesis - Order and structure - Winner

Structured browsing. The assumption is that the user scrolls from top to bottom and looks for the products that are interesting. In this behaviour, we want to group different types of products (context) in a structured way and list the products in groups from the most relevant context to the least relevant.

For example, a listing on a brand might generate all the pants first, followed by all the jackets, boots, etc. Within each group, the products are sorted based on things like popularity, boost & bury rules, personalisation.

Working further with it the products can also be grouped into sub-groups of, for example, price or other ways of differentiating the products.

The results

I
+

0

%

Average Order Value

I (1)
+

0

%

Average Session Value

I (2)
+

0

%

Average Price

I (3)
+

0

%

Revenue Increase

Pic (3)

D - Boost of campaign products (XXLs existing solution based on Apache Solr)

 

Conclusion

For XXL the Order and structure Hypothesis performed best during the test period on all metrics and with a revenue increase from the navigation of 12.68 % compared to XXLs existing solution. The overall revenue increase was 4,5%. Lightweight Lucy also performed well on revenue but with a decrease in AOV.

XXL decided to continue with Order and structure as their solution for category navigation.

Ill_07 1

Loop54 offers true personalised on-site product search and category navigation

Shoppers expect the same level of relevance and personalisation online as they experience in-store. Powered by Machine Learning and built exclusively for eCommerce, Loop54 delivers that exceptional online shopping experience.

  • Automated: Automatically learns words and merchandises search and category listings
  • Relevant: Interprets search intent to deliver truly relevant results
  • Personalised: Sorts results according to popularity and personal taste

REQUEST A DEMO TODAY!