Long Term Recommender Benchmarking for Mobile Shopping List Applications using Markov Chains
Sandro Schopfer, Thorben Keller, Cosibon Ag · Alexandria (UniSG) (University of St.Gallen) · 2014
This paper presents a method to estimate the performance and success rate of a recommender system for digital shop-ping lists. The list contains a number of items that are allowed to occupy three different states (to be purchased, purchased and deleted) as a function of time. Using Markov chains, the probability distribution function over time can be estimated for each state, and thus, the probability that a rec-ommendation is deleted from the list can be used to bench-mark a recommender on its endurance and performance. An experimental set up is described that allows to test the pre-sented method in an actual mobile application. The appli-cation of the method will allow to benchmark a variety of recommenders. An outlook is given on how the presented method can be used iteratively to support a recommender in finding the user’s favourite items/products. 1.