Evaluating Music Recommendations with Binary Feedback for Multiple Stakeholders

7 Pages Posted: 10 Sep 2021

See all articles by Sasha Stoikov

Sasha Stoikov

Cornell Financial Engineering Manhattan

Hongyi Wen

Cornell University

Date Written: September 7, 2021


High quality user feedback data is essential to training and evaluating a successful music recommendation system, particularly one that has to balance the needs of multiple stakeholders. Most existing music datasets suffer from noisy feedback and self-selection biases inherent in the data collected by music platforms. Using the Piki Music dataset of 500k ratings collected over a two-year time period, we evaluate the performance of classic recommendation algorithms on three important stakeholders: consumers, well-known artists and lesser-known artists. We show that a matrix factorization algorithm trained on both likes and dislikes performs significantly better compared to one trained only on likes for all three stakeholders.

Keywords: Datasets, Music recommendations, Multi-stakeholders, Recommendation Systems

Suggested Citation

Stoikov, Sasha and Wen, Hongyi, Evaluating Music Recommendations with Binary Feedback for Multiple Stakeholders (September 7, 2021). Available at SSRN: https://ssrn.com/abstract=3919046

Sasha Stoikov (Contact Author)

Cornell Financial Engineering Manhattan ( email )

2 W Loop Rd
New York, NY New York 10044
United States

HOME PAGE: http://www.sashastoikov.com

Hongyi Wen

Cornell University ( email )

Ithaca, NY 14853
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics