Blockbuster Culture's Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity

By Daniel M. Fleder, Kartik Hosanagar. Management Sciences, 2009

438 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Marketing

View Paper: https://www.semanticscholar.org/paper/995e6695fd6b23d3d50bd78a0d9ae58e826fcc0f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Marketing

Citations in the corpus

The long tail of recommender systems and how to leverage it (2008, background): “Also [3] studied the effects of recommender systems on sales concentration and did not address the problem of improving recommendations for the items in the Long Tail, which constitutes the focus of this paper.”
Music recommendation and discovery in the long tail (2008, background): “In fact, recommenders that appropriately discount popularity may increase total sales, as well as potentially increase the margins by suggesting more novel, or less known, products (Fleder and Hosanagar, 2007).”
Novelty and Diversity in Recommender Systems (2015, background): “Businesses are accounting for these aspects when engineering recommendation functionalities, and researchers have started to seek principled foundations for incorporating novelty and diversity in the recommendation models, algorithms, theories, and evaluation methodologies [7,11,20,22].”
Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques (2012, methodology): “On the other hand, another study [14] shows a contradictory finding that recommender systems actually can reduce the aggregate diversity in sales.”
Recommender systems: from algorithms to user experience (2012, background): “Fleder and Hosanger (2009) have pursued the question of what will happen in ecommerce as recommenders are ubiquitous.”
The Limits of Popularity-Based Recommendations, and the Role of Social Ties (2016, background): “To the best of our knowledge, the only theoretical investigation on the market eﬀects of RS’s is [12].”
Understanding User Beliefs About Algorithmic Curation in the Facebook News Feed (2015, result): “In addition, in two separate modeling and simulation studies, independent research teams found that some recommendation algorithms are susceptible to a narrowing effect under particular conditions; however, neither paper presented empirical data to verify the simulation results [11, 17].”
The Effect of Recommendations on Network Structure (2016, background): “This ﬁnding, however, is at odds with informal and theoretical arguments that suggest recommendation systems (at least collaborative ﬁlters) recommend the most popular products disproportionately often (i.e., superlinearly in their market share) [13].”
Do I Follow My Friends or the Crowd? Information Cascades in Online Movie Ratings (2015, neutral): “Such a model would have application beyond de-biasing rating systems given recent research that show the existence of similar path dependence in a number of online systems, ranging from recommender systems (Fleder and Hosanagar 2009) to search engine ranking mechanisms (Cho and Roy 2004).”
Diversity, Serendipity, Novelty, and Coverage (2016, background): “Rather than providing formal definitions of serendipity, early works analyzed the process of serendipitous information discovery and the paradox of designing for unexpected results [Foster and Ford 2003; McBirnie 2008]. In the RS literature, Herlocker et al. [2004] informally defined a serendipitous”
Developing a Price-Sensitive Recommender System to Improve Accuracy and Business Performance of Ecommerce Applications (2015, background): “Fleder and Hosanagar 13 demonstrated that RS that discount item popularity in the selection of recommendable items may increase sales more than RS that do not.”
Exploring the filter bubble: the effect of using recommender systems on content diversity (2014, background): “Fleder et al. [2], in their simulation study about the effect of recommender systems on sales’ diversity, argued that at the user-user level, users are directed towards a common experience.”
From hits to niches?: or how popular artists can bias music recommendation and discovery (2008, background): “In fact, recommenders that appropriately discount popularity may increase total sales [9], as well as potentially increase the margins by suggesting more novel or less known tunes.”
Model-Based Purchase Predictions for Large Assortments (2016, background): “Such recommendations might even be perceived as trivial or boring (Fleder and Hosanagar, 2009).”