I let movielens . org mine my movie preferences- the data is interesting. I've rated 472 movies across their 19 overlapping genres. My average rating is 3.4 and I average ~72 ratings per genre. Some more than others-- 195 in action, 1 each in Documetary and TV Movie.
#moviesky
#moviesky
September 25, 2026 at 4:05 PM
I let movielens . org mine my movie preferences- the data is interesting. I've rated 472 movies across their 19 overlapping genres. My average rating is 3.4 and I average ~72 ratings per genre. Some more than others-- 195 in action, 1 each in Documetary and TV Movie.
#moviesky
#moviesky
Nice. I'm going to go answer this blind and see how different. It also reminds me of movielens dot org, which tracks your movie ratings across genres like, history, documentary, war, western, music, mystery, etc (to name the ones that, weirdly, are my high scores).
September 25, 2026 at 3:14 PM
Nice. I'm going to go answer this blind and see how different. It also reminds me of movielens dot org, which tracks your movie ratings across genres like, history, documentary, war, western, music, mystery, etc (to name the ones that, weirdly, are my high scores).
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
September 9, 2026 at 10:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Homework 4 EECS 349 Answered
1) Collaborative Filtering: Looking at the Data (2 points) When doing machine learning, it is important to have an understanding of the dataset that you will be working on. On the course website under “links” there is a link to the MovieLens dataset. You will use the…
1) Collaborative Filtering: Looking at the Data (2 points) When doing machine learning, it is important to have an understanding of the dataset that you will be working on. On the course website under “links” there is a link to the MovieLens dataset. You will use the…
Homework 4 EECS 349 Answered
1) Collaborative Filtering: Looking at the Data (2 points) When doing machine learning, it is important to have an understanding of the dataset that you will be working on. On the course website under “links” there is a link to the MovieLens dataset. You will use the MovieLens 100K dataset to build a collaborative filter to predict the rating a user may give to a movie they haven’t seen.
jarviscodinghub.com
September 8, 2026 at 12:54 PM
Homework 4 EECS 349 Answered
1) Collaborative Filtering: Looking at the Data (2 points) When doing machine learning, it is important to have an understanding of the dataset that you will be working on. On the course website under “links” there is a link to the MovieLens dataset. You will use the…
1) Collaborative Filtering: Looking at the Data (2 points) When doing machine learning, it is important to have an understanding of the dataset that you will be working on. On the course website under “links” there is a link to the MovieLens dataset. You will use the…
Assignment 1 CSE 512 Answered
The required task is to simulate data partitioning approaches on-top of an open source relational database management system (i.e., PostgreSQL). Each student must generate a set of Python functions that load the input data into a relational table, partition the table…
The required task is to simulate data partitioning approaches on-top of an open source relational database management system (i.e., PostgreSQL). Each student must generate a set of Python functions that load the input data into a relational table, partition the table…
Assignment 1 CSE 512 Answered
The required task is to simulate data partitioning approaches on-top of an open source relational database management system (i.e., PostgreSQL). Each student must generate a set of Python functions that load the input data into a relational table, partition the table using different horizontal fragmentation approaches, and insert new tuples into the rightfragment. Input Data. The input data is a Movie Rating data set collected from the MovieLens web site…
jarviscodinghub.com
September 8, 2026 at 8:41 AM
Assignment 1 CSE 512 Answered
The required task is to simulate data partitioning approaches on-top of an open source relational database management system (i.e., PostgreSQL). Each student must generate a set of Python functions that load the input data into a relational table, partition the table…
The required task is to simulate data partitioning approaches on-top of an open source relational database management system (i.e., PostgreSQL). Each student must generate a set of Python functions that load the input data into a relational table, partition the table…
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
August 30, 2026 at 12:00 AM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
August 22, 2026 at 9:00 AM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
「昔は良かった」の昔は、自分が生まれる前を指している。
映画評価データMovieLensの100万件超の分析で、人は自分の生まれる前の作品を高く評価し、自分の登場前後から質が落ちたと感じる傾向が全世代で一致した。
黄金期は、世代ごとに移動する。
映画評価データMovieLensの100万件超の分析で、人は自分の生まれる前の作品を高く評価し、自分の登場前後から質が落ちたと感じる傾向が全世代で一致した。
黄金期は、世代ごとに移動する。
August 8, 2026 at 1:13 AM
「昔は良かった」の昔は、自分が生まれる前を指している。
映画評価データMovieLensの100万件超の分析で、人は自分の生まれる前の作品を高く評価し、自分の登場前後から質が落ちたと感じる傾向が全世代で一致した。
黄金期は、世代ごとに移動する。
映画評価データMovieLensの100万件超の分析で、人は自分の生まれる前の作品を高く評価し、自分の登場前後から質が落ちたと感じる傾向が全世代で一致した。
黄金期は、世代ごとに移動する。
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
July 29, 2026 at 7:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
I noticed that I can download all (or a big chunk of) my data on Movielens, the site where I rate movies (a free service of the University of Minnesota). So I downloaded the two relevant files and thought, as always, R will make quick work of this. I think […]
[Original post on mathstodon.xyz]
[Original post on mathstodon.xyz]
July 21, 2026 at 6:51 AM
I noticed that I can download all (or a big chunk of) my data on Movielens, the site where I rate movies (a free service of the University of Minnesota). So I downloaded the two relevant files and thought, as always, R will make quick work of this. I think […]
[Original post on mathstodon.xyz]
[Original post on mathstodon.xyz]
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
June 21, 2026 at 11:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
June 13, 2026 at 1:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
今日のZennトレンド
推薦システムの新たなパラダイム Generative Recommendation
Generative Recommendation（GR）は、推薦を言語モデルのように「次のアイテムIDを自己回帰的に生成する問題」として定式化する手法です。
モデル規模に応じて性能が向上するスケーリング則を適用できる利点があります。
膨大なアイテム数やコールドスタート問題への対策として、コンテンツ情報をトークン列で表現するSemantic IDを導入します。
記事では、MovieLensを用いた具体的な実装フローについて解説しています。
推薦システムの新たなパラダイム Generative Recommendation
Generative Recommendation（GR）は、推薦を言語モデルのように「次のアイテムIDを自己回帰的に生成する問題」として定式化する手法です。
モデル規模に応じて性能が向上するスケーリング則を適用できる利点があります。
膨大なアイテム数やコールドスタート問題への対策として、コンテンツ情報をトークン列で表現するSemantic IDを導入します。
記事では、MovieLensを用いた具体的な実装フローについて解説しています。
推薦システムの新たなパラダイム Generative Recommendation
近年Meta[1] [2]、ByteDance[3]、Kuaishou[4]、Google[5]、Alibaba[6]といったビッグテックの企業から、Generative Recommendationに関する手法が数多く発表されています。これは、推薦システムの問題設定を新しい形で定義するもので、RecSys、CIKM、WWWなどの学会でもチュートリアルが開かれたりとホットなトピックになっています。
zenn.dev
June 8, 2026 at 1:00 PM
今日のZennトレンド
推薦システムの新たなパラダイム Generative Recommendation
Generative Recommendation（GR）は、推薦を言語モデルのように「次のアイテムIDを自己回帰的に生成する問題」として定式化する手法です。
モデル規模に応じて性能が向上するスケーリング則を適用できる利点があります。
膨大なアイテム数やコールドスタート問題への対策として、コンテンツ情報をトークン列で表現するSemantic IDを導入します。
記事では、MovieLensを用いた具体的な実装フローについて解説しています。
推薦システムの新たなパラダイム Generative Recommendation
Generative Recommendation（GR）は、推薦を言語モデルのように「次のアイテムIDを自己回帰的に生成する問題」として定式化する手法です。
モデル規模に応じて性能が向上するスケーリング則を適用できる利点があります。
膨大なアイテム数やコールドスタート問題への対策として、コンテンツ情報をトークン列で表現するSemantic IDを導入します。
記事では、MovieLensを用いた具体的な実装フローについて解説しています。
The arxiv paper has enough detail that I think you can straight up reproduce it w/ CC. I'm trying it out w/ MovieLens
arxiv.org/pdf/2511.14881
arxiv.org/pdf/2511.14881
arxiv.org
May 29, 2026 at 2:58 AM
The arxiv paper has enough detail that I think you can straight up reproduce it w/ CC. I'm trying it out w/ MovieLens
arxiv.org/pdf/2511.14881
arxiv.org/pdf/2511.14881
HSTU From Scratch in PyTorch - A complete Walkthrough • RecSys for MLEs Part 9d: data pipeline, three sub-layers, retrieval + rating loss, and benchmarking against rectools' HSTU on MovieLens-1M
HSTU From Scratch in PyTorch - A complete Walkthrough
RecSys for MLEs Part 9d: data pipeline, three sub-layers, retrieval + rating loss, and benchmarking against rectools' HSTU on MovieLens-1M
www.mlwhiz.com
May 28, 2026 at 5:13 AM
HSTU From Scratch in PyTorch - A complete Walkthrough • RecSys for MLEs Part 9d: data pipeline, three sub-layers, retrieval + rating loss, and benchmarking against rectools' HSTU on MovieLens-1M
BLADERUNNER 2049
youtube.com/shorts/SBL3a...
youtube.com/shorts/SBL3a...
Behind The Scenes - Blade Runner 2049
YouTube video by MovieLens
youtube.com
May 15, 2026 at 11:16 PM
BLADERUNNER 2049
youtube.com/shorts/SBL3a...
youtube.com/shorts/SBL3a...
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
May 10, 2026 at 6:00 AM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
CC SATANIC FOLLYWOOD
Stanley Kubrick's Mysterious Death After Eyes Wide Shut 🤔🎥
YouTube video by MovieLens
youtube.com
April 29, 2026 at 12:09 PM
CC SATANIC FOLLYWOOD
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
April 27, 2026 at 1:00 AM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
April 18, 2026 at 4:00 AM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
April 12, 2026 at 4:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Using MovieLens ratings.
April 7, 2026 at 8:54 PM
Using MovieLens ratings.
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
April 4, 2026 at 9:00 PM
movielens_100k: MovieLens 100K (1998).
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram:
Three bipartite networks that make up the MovieLens 100K Dataset, a stable benchmark dataset of 100,000 ratings from 1000 users on 1700 movies.
24129 nodes, 95580 edges.
https://networks.skewed.de/net/movielens_100k
Ridiculogram: