CR Increasing


The client  is a large fashion e-commerce retailer with more than 200,000 unique visitors a day. There was no mechanism for a goods list that sorted goods for any commercial factors. The list of products was simply displayed randomly.

The client had worked with contractors, who were suppliers of saas-solutions for sorting algorithms. As a result, it was decided to develop the client’s own algorithm, which would have priority for goods which have a higher probability to be bought.


⁠It was complicated for the client to determine the popularity of each product. We had to carefully analyze the business operations of the fashion retailer, conduct several consultations and perform analytics in order to formalize the requirements for the future algorithm.

The task was further complicated by the fact that representatives of the client wanted to create a manual moderation of the product list, in addition to the algorithm.  They wanted to have the ability for their merchandising experts to manually move the goods among themselves, supplementing the algorithm.


An algorithm with machine learning elements was developed. Once a day, it forms  an index of popularity for each SKU (product), taking into account the following parameters:

  • Seasonal factor for categories (a table was created, where each category of goods for each calendar week is ranked)
  • Brand weight (calculated by a complex formula, based on the current stock for each brand for each category and the margin ratio – mark-up)
  • Product sizes with the allocation of the key sizes (kernels) for each group of the goods.

A number of other less important parameters were also taken into account. The weight of each factor can be adjusted separately. As a result, according to a complicated formula, the index of popularity of all goods has been updated each night and a product list created for the next day.


The algorithm that was developed with manual moderation allowed an increase of the average CR by 14.29% within the first month of use.In a single season (6 months),  the customer received more than 2.2M euros of additional profit.