Music Recommendations at Scale with Spark
The document discusses the development of music recommendation systems at Spotify, primarily focusing on collaborative filtering and matrix factorization techniques. It details methods such as explicit and implicit matrix factorization, as well as the application of Hadoop and Spark for scaling these recommendations. The presentation highlights the evolution of these algorithms and the challenges
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GitHub - spotify/featran: A Scala feature transformation library for data science and machine learning
GitHub - spotify/annoy: Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
