SweetRS: Dataset for a recommender systems of sweets

TL;DR

This paper introduces SweetRS, a new dataset of user ratings for candies and sweets, facilitating benchmarking recommender systems with real-world data and demonstrating the effectiveness of the Soft-Impute algorithm.

Contribution

The paper presents a novel dataset for recommender systems involving sweets and provides benchmark results using the Soft-Impute algorithm.

Findings

28% matrix coverage in the dataset

Over 44,000 user ratings collected

Soft-Impute performs effectively on this dataset

Abstract

Benchmarking recommender system and matrix completion algorithms could be greatly simplified if the entire matrix was known. We built a \url{sweetrs.org} platform with $77$ candies and sweets to rank. Over $2000$ users submitted over $44000$ grades resulting in a matrix with $28\%$ coverage. In this report, we give the full description of the environment and we benchmark the \textsc{Soft-Impute} algorithm on the dataset.