Data-driven decision-making and personalization have recently emerged as methods with high utility for many different applications. We integrate personalization into our search application to provide user-specific search. Data such as browser type, operating system, type of device, time of day, time of year, or location allow conclusions to be drawn about the user and their needs. The geographic classification of customers is based on the Nielsen areas known from market research within Germany and, if relevant for the store, country-based outside Germany. It is therefore easy to imagine that the owner of an iPhone in Berlin at 10 a.m. and the owner of a Windows 7 PC in Lower Bavaria at 6 p.m. have completely different needs for the same search.

The best thing about personalization, however, is that it does not use ideas or insider knowledge to categorize users, as this is purely derived from the collective behavior of other users. The prerequisite for this possibility is, of course, the collection of data that comes before the adaptation of search results. Only when enough statistically significant data has been collected and the values for the personalization model have been converged, it can be activated in the Makaira backend.

With this search, it is now possible to present visitors from different user groups with a better search experience tailored to them, and this in turn has an impact on the conversion rate.

The processing of the search results by personalization is carried out by means of Rescoring. Thus, the content level of the search comes first, followed by the individual selection of suitable products for the user.

Grouping fields in personalization

Makaira internally uses fields of your search index to group products that are affected by the personalization. In contrast to a product-specific rescoring this prevents the rise of single products in the listings that will never change its position and allow also for newcomer-products. In order to be fully functional, Makaira needs two fields. By default, this is the manufacturer_title and the maincategory. We require that:

  1. At least 50% of the products (makaira-productgroup) have set this field and
  2. That not more than 80% of all products are in one group.

If your data does not fulfill these requirements, either fill the fields with appropriate values or contact the support to change the used fields or give more advice.