The MovieLens datasets, first released in 1998, describe people’s expressed preferences for movies. These preferences take the form of tuples, each the result of a person expressing a preference (a 0-5 star rating) for a movie at a particular time. These preferences were entered by way of the MovieLens web site1 — a recommender system that asks its users to give movie ratings in order to receive personalized movie recommendations.
Source: The MovieLens Datasets: History and Context
Image Source: http://files.grouplens.org/papers/harper-tiis2015.pdf
Variants: MovieLens, MovieLens 100K, MovieLens 1M, MovieLens 10M, MovieLens 20M, MovieLens-Latest, MovieLens 25M
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Click-Through Rate Prediction | TF4CTR | TF4CTR: Twin Focus Framework for … | 2024-05-06 |
| Click-Through Rate Prediction | FinalMLP | FinalMLP: An Enhanced Two-Stream MLP … | 2023-04-03 |
| Click-Through Rate Prediction | AFN+ | Adaptive Factorization Network: Learning Adaptive-Order … | 2019-09-07 |
Recent papers with results on this dataset: