(This blog post is based on the research article ‘A social recommender mechanism for e-commerce: Combining similarity, trust, and relationship’ by Li, Wu and Lai, 2013)
In a world where there is not only a massive selection of different products but also the internet that enables us to theoretically choose among all those offerings without the high search costs that have hindered us from an informed choice in the past, the problem of information overload is a challenge for both the consumers and the companies offering those products (Li, Kauffman, Van Heck, Vervest and Dellaert, 2014). As explained by Murray and Häubl (2009), especially in the e-commerce environment, good recommender systems (RS) that aid the consumer in finding the right product are becoming increasingly important, ensuring a higher consumer satisfaction and increased sales for the offering companies (Li, Wu and Lai, 2013). Even though good RSs exist in the market (such as Amazon’s collaborative item-to-item filtering mechanism or Netflix’s hybrid model of collaborative and content based filtering (Jones, 2013)), it seems that today’s RSs fall behind what should be technically possible. Thus, Li et al. (2013) suggest a new RS that does not only take a customer’s past behavior into account but adds a social component that would greatly increase the information available to the system and thus improve its prediction accuracy. An important drawback of today’s RSs mentioned by Li et al. (2013) is that the platforms utilizing RSs are independently operated and only use the data obtained within the boundaries of their respective platform. Real value, however, could be obtained when integrating the data of various different platforms and adding the social component of the social network of a consumer to the recommendations shown on an e-commerce platform. In real life, after all, we also tend to ask our friends for advice when shopping and especially in cliques of close friends, the shopping behavior of individuals potentially influences the shopping behavior of the others (Li et al., 2013; Shang, Hui, Kulkarni and Cuff, 2011). In total, the RS developed and tested by Li et al. (2013) in an empirical experiment comprises four elements that work together to produce highly accurate recommendations. These are
- a preference similarity analysis module that takes into account how similar customers have rated a certain product (recommendation source: similar people)
- a recommendation trust analysis module, which computes the success of the product recommendations of a customer according to his/ her product ratings (i.e. the reputation quality of “experts”) (recommendation source: experts)
- a social relation analysis module that takes into account the behavior of close friends, computing the closeness between two actors (recommendation source: close friends)
- a personalized product recommendation module that factors in the personalized factor weights of a customer (i.e. his evaluation of what is important to him in a recommendation).
The experiment conducted by Li et al. (2013) yields interesting results but is also subject to very interesting limitations. First of all, it was shown that a RS considering different sources of information (resembling real life advice-seeking situations) but also balancing these sources according to the consumer’s preferences significantly outperforms the average RS.
(Li et al., 2013, p. 747)
What is also interesting and valuable for e-commerce retailers is that even though the best recommendations are made when a customer’s preferences are explicitly known, the system is still able to give very accurate recommendations when extrapolating other people’s preferences for certain product categories (e.g. people in general prefer expert opinions over a friend’s opinion when purchasing consumer electronics, while individual preferences and friends’ opinions are more highly valued for entertainment & living products). As the article discussed is already two years old, one would assume that by now, such valuable overarching RSs existed. In academia, indeed more researchers have picked up on the idea and have suggested different methods to include social information in e-commerce RSs. Nevertheless, in practice no such system has been implemented or at least no provider has managed to successfully establish such a system in the market. The potential reason for this is also one of the most important limitations of Li et al.’s article: the lack of cross-platform personalized RSs is caused on the one hand by platform constraints, but more importantly by data privacy issues. In a time where many users are already uncomfortable with the uncertainty about what exactly is done with their data, I assume that few would agree to having their data shared across different platforms so that an even more detailed profile of them is created that is widely accessible to many different platform providers. I personally, would not see the added value of more personalized and accurate recommendations when giving up the last impression of privacy and data security is the price I’d have to pay. What is your opinion about this? Do you think that cross-platform social RSs are the next step in this journey or do you think that eventually this trend of giving up more and more of one’s data will slow down?
Jones, T. (2013, December 12). Recommender Systems Part 1: Introduction to approaches and algorithms. IBM developer works. Retrieved on April 4, 2015 from: http://www.ibm.com/developerworks/library/os-recommender1/
Li, T., Kauffman, R. J., van Heck, E., Vervest, P., & Dellaert, B. G. (2014). Consumer Informedness and Firm Information Strategy. Information Systems Research, 25(2), 345-363.
Li, Y. M., Wu, C. T., & Lai, C. Y. (2013). A social recommender mechanism for e-commerce: Combining similarity, trust, and relationship. Decision Support Systems, 55(3), 740-752.
Murray, K. B., & Häubl, G. (2009). Personalization without interrogation: Towards more effective interactions between consumers and feature-based recommendation agents. Journal of Interactive Marketing, 23(2), 138-146.
Shang, S., Hui, P., Kulkarni, S. R., & Cuff, P. W. (2011). Wisdom of the crowd: Incorporating social influence in recommendation models. In Parallel and Distributed Systems (ICPADS), 2011 IEEE 17th International Conference on (pp. 835-840). IEEE.
http://pixabay.com/de/system-netz-nachrichten-personen-571182/ (license: CC0 public domain)