This informative (and interesting) talk introduced some of the concepts involved in developing personalisation algorithms for the grocery retail sector, and discussed wider aspects such as the business challenges that have or are likely to be addressed.
The talk used the work of Unilever's Mathematics & Informatics group to illustrate how recommender system work. This group has been investigating various personalisation algorithms, in order to understand how their performance varies according to different data sets and application scenarios. The work of the group was illustrated by examples, the group has been working on, including the Swiss online supermarket LeShop (www.LeShop.ch), in analysing individual shopping basket (cf. loyalty card) data. As part of this collaboration, an on-line personalised retail recommender systems was developed, which also serve as a test-bed to evaluate the performance of their personalisation algorithms.