A multiple criteria approach integrating social ties to support purchase decision

To leverage information sharing in online social networks, online retailers (e-tailers) have launched social networking functions on their platforms. The objective of e-tailers’ social networks is to empower consumers to connect and share product information. However, the e-tailers have not used these social networks to provide product recommendations to customers. Our goal is to aid e-retailers in personalizing recommendations for customers using their friends’ (referrers’) preferences. Our approach involves: (a) mapping the referrers’ online behaviors into a set of pairwise comparisons, and use additive value functions to model their preferences, (b) defining the degree of contextual trust of a customer towards a referrer to differentiate the roles of referrers, (c) proposing a clustering algorithm to capture referrers’ heterogeneous preferences, and (d) aggregating preference information for referrers within the same subgroup to obtain diversified recommendations. On a broader note, this study illustrates how online information (i.e., preference expressions of referrers, social ties between a consumer and referrers) from an e-tailer's social network can be mined and incorporated into a decision-aiding approach to generate tailor-made recommendations for customers. Finally, we illustrate the proposed approach to with a numerical case study.