Built a recommender on a large public dataset, the unglamorous matrix-factorization kind that actually ships.
#Recommenders #MachineLearning

MovieLens 32M is a useful recommender-systems benchmark: 32M ratings and 2M tag applications across 87,585 movies by 200,948 users.

Good for testing ranking models, bias by genre/year, and cold-start splits.

https://grouplens.org/datasets/movielens/32m/

#OpenData #Recommenders