Intelligent product search with soft-boundary preference relaxation

Abstract

Abstract. This paper proposes a novel method for preference relaxation in online product search, which enables consumers to make quality choices without suffering from the commonly experienced information overload. In online shopping scenarios that involve multi-attribute choice tasks, it can be difficult for consumers to process the vast amounts of information available and to make satisfactory buying decisions. In such situations consumers are likely to eliminate potentially good choices early on, using hard-constraint filtering tools. Our approach uses edge sets to identify the alternatives on the soft boundary and the principle of alternative domination to suppress the alternatives on this boundary that are irrelevant. We demonstrate how our approach outperforms existing methods for product search in a set of simulations using two sets of 2650 car advertisements and 1813 digital cameras gathered from a popular online store.

The performance of recommender systems in online shopping: A user-centric study

“…We show that the use of preference relaxation in product search is a valuable approach to product recommendation. Our user experiment demonstrates that classical approaches to preference relaxation (Mirzadeh & Ricci, 2007) fail to increase consumers' decision-making performance despite promising results achieved in previous work (Dabrowski et al, 2012). We show that although the results of previous studies suggest positive effects of the Standard Preference Relaxation (see Section 3) on decision performance, the strong negative effects on decision effort compromise the potential gain in decision quality.…”

“…The user experiment described in this paper provides additional insights to the study using a set of simulations recently carried out by Dabrowski and Acton (Dabrowski et al, 2012) using the leave-one-out approach (McSherry, 2004). Dabrowski and Acton's results showed that Standard Preference Relaxation might have a positive effect on decision quality, yet it can lead to a significant increase in the average number of alternatives in result sets, which negatively impacts decision-making effort.…”

“…Building upon and extending recent work by Dabrowski and colleagues (Dabrowski, Acton, & Van der Heijden, 2012) wherein various preference relaxation techniques were employed in a series of simulations, we evaluate their approach in a user study with a larger data set and compare our findings to the results of their simulations. Each of the 111 participants of our user experiment was asked to choose a car from a set of 45278 actual advertisements published by the biggest used car portal in Ireland.…”

“…This approach, referred to as Standard Preference Relaxation (SR), often leads to a very large number of alternatives presented to the user (Dabrowski et al, 2012), resulting in information overload and increasing decision effort (Turetken & Sharda, 2004). This problem is addressed by the Soft-Boundary Preference Relaxation approach.…”

“…Each of the 111 participants of our user experiment was asked to choose a car from a set of 45278 actual advertisements published by the biggest used car portal in Ireland. The experiment focused on user-centric measures of decision performance including decision quality and effort, in contrast to the set of simulations described by Dabrowski and Acton (Dabrowski et al, 2012), where the effect of decision quality and effort were measured without user participation. We show that our user experiment enhances that study by providing new insights to decision-making performance of preference relaxation in product search and accordingly, we suggest possible improvements to the method directly applicable to online retailers.…”