Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. Reconciling the Accuracy-Diversity Trade-off in Recommendations

Reconciling the Accuracy-Diversity Trade-off in Recommendations

Thumbnail Image
Download
Name

3589334.3645625.pdf

Size

1.57 MB

Format

Adobe PDF

Checksum (MD5)

ed47592a78a03c9306968fa9c5aff4d1

Download all files submitted through automated deposit
3589334.3645625.zip (1.38 MB)
Author(s)
Peng, Kenny
•
Raghavan, Manish
•
Pierson, Emma
•
Kleinberg, Jon
•
Garg, Nikhil
Date Issued
May 13, 2024
Publisher
ACM
Citation
Peng, Kenny, Raghavan, Manish, Pierson, Emma, Kleinberg, Jon and Garg, Nikhil. 2024. "Reconciling the Accuracy-Diversity Trade-off in Recommendations."
Version
Final published version
Abstract
When making recommendations, there is an apparent trade-off between the goals of accuracy (to recommend items a user is most likely to want) and diversity (to recommend items representing a range of categories). As such, real-world recommender systems often explicitly incorporate diversity into recommendations, at the cost of accuracy. We study the accuracy-diversity trade-off by bringing in a third concept: user utility. We argue that accuracy is misaligned with user utility because it fails to incorporate a user's consumption constraints: at any given time, users can typically only use at most a few recommended items (e.g., dine at one restaurant, or watch a couple of movies). In a theoretical model, we show that utility-maximizing recommendations---when accounting for consumption constraints---are naturally diverse due to diminishing returns of recommending similar items. Therefore, while increasing diversity may come at the cost of accuracy, it can also help align accuracy-based recommendations toward the more fundamental objective of user utility. Our theoretical results yield practical guidance into how recommendations should incorporate diversity to serve user ends.
Description
WWW ’24: Proceedings of the ACM on Web Conference May 13–17, 2024, Singapore, Singapore
MIT Department
Sloan School of Management
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
https://hdl.handle.net/1721.1/155156
DOI of Published Version
https://doi.org/10.1145/3589334.3645625
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.