The Collaborative Filtering Effect of Netflix Ratings for Indie Films versus Blockbusters
and Heavy Users versus Casual Users

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fkg264nx8244" class="su-underline">Show Content</a>

Abstract/Contents

Abstract: Collaborative filtering algorithms, whose adoption by online recommendation engines has markedly increased in recent years, serve to match users with items based on what they have consumed in the past or the tastes of similar users. Meanwhile, Internet economists and marketing experts have cited a new phenomenon driven by online platforms called the "Long Tail," which is a distributional shift towards lesser-known niche products. In this paper, I test whether an online platform that uses a collaborative filtering algorithm can help match non-mass market goods with previously un-informed demanders and how this can affect user heterogeneity. I choose to examine movie ratings made publicly available in the Netflix Prize, an open source competition to improve the existing algorithm used for Netflix recommendations. Looking at demand across different movie categories, I find a stronger responsiveness of demand to early user ratings for indie films, relative to blockbusters. This effect is further magnified for "heavier" users with greater rating histories. As movie "buffs" with more variety in tastes, these users not only are greater influencers of demand, but are also more inclined to be influenced by others in their own demand, in contrast to what one observes on other online platforms.

Type of resource	text
Date created	May 2014

Author	Tang, Henry Zhu
Primary advisor	Bresnahan, Timothy
Degree granting institution	Stanford University, Department of Economics

Subject	Long Tail
Subject	indie
Subject	collaborative filtering
Subject	recommendations
Subject	heavy users
Subject	Netflix
Subject	Stanford Department of Economics
Genre	Thesis

Location	https://purl.stanford.edu/kg264nx8244

Use and reproduction: User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.

Preferred Citation: Tang, Henry Zhu. (2014). The Collaborative Filtering Effect of Netflix Ratings for Indie Films versus Blockbusters and Heavy Users versus Casual Users. Stanford Digital Repository. Available at: https://purl.stanford.edu/kg264nx8244

Stanford University, Department of Economics, Honors Theses

Loading usage metrics...