An approach to modelling implicit user feedback for optimising e-commerce search

More than other domains, e-commerce search depends on implicit user feedback to optimise search result ranking as buying decision criteria such as ‘an attractive price’ and ‘brand sympathy’ are very hard to make explicit. On the other hand, this decision making can be observed implicitly in web tracking.

E-commerce search cannot just use more generally known approaches to click modelling. For example, the common assumption that users would view search results sequentially doesn’t hold for grid layouts and our model will will have to deal with further contextual biases such as the device type or even time of the day.

In this talk, I shall introduce an approach to using implicit user feedback based on Bayesian hierarchical modelling. It will provide a solution for dealing with contextual biases more generally. The model will cope with varying quantities of observations and it allows to incorporate different types of events, such as clicks and checkouts.

René Kriegler

OpenSource Connections

René has worked in search for almost 15 years, including on projects for some of the top 10 German e-commerce sites. He is co-founder and co-organiser of MICES (Mix-Camp E-commerce Search), an event that brings together the e-commerce search community each year. His technological focus is on Solr, Elasticsearch and Lucene. He created and maintains the Querqy open source library for query rewriting. René is co-initiator of the Chorus project – an open source software stack that combines Querqy with other powerful tools to build e-commerce search and to measure and improve search quality.