I am looking for a 3-dimensional valued dataset to test my tri-clustering method. I hope to find something like a movie rating database with dimensions for user-movie-genre and ratings depending on both movie and genre (e.g. user rates the movie as a 5-star horror, 3-star thriller, or 1-star comedy).

Any fields will do. Only the structure of the data is important.


A good place to start looking for datasets is the Machine Learning Repository from UCI.

There are a few datasets that stand out for your method. Although they may not match exactly, you may get some ideas.

You can use the table columns "Default Task", "Attribute Types", and "# Attributes" to help narrow down more possible data sets.

| improve this answer | |

You can find clustering datasets that are publicly available by googling. Here are a few more:

KEEL - http://sci2s.ugr.es/keel/datasets.php

ResearchGate Forum / Do you know any free large-scale dataset for clustering? - http://www.researchgate.net/post/Do_you_know_any_free_large-scale_dataset_for_clustering

University of Illinois - Intelligent Data Set - http://uisacad2.uis.edu/dstar/data/clusteringdata.html

University of Koln - http://www.uni-koeln.de/themen/statistik/data/cluster/

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.