RapidMiner (formerly YALE, Yet Another Learning Environment) was developed starting in 2001 by Ralf Klinkenberg, Ingo Mierswa, and Simon Fischer at the Artificial Intelligence Unit of the Technical University of Dortmund. It is developed on an open core model. It is written in the Java programming language and is a cross-platform framework. RapidMiner supports interactive mode (GUI), command-line interface (CLI) and Java API. RapidMiner is mainly proprietary commercial product since version 6.0. However it offers a free edition limited to one logical processor and 10,000 data rows, which is available under the AGPL license.

For large-scale data analytics, RapidMiner supports unsupervised learning in Hadoop [Radoop], supervised learning in memory with scoring on the cluster (SparkRM), and supervised learning and scoring with native algorithms on the cluster. In this case, the algorithm coverage is narrowed into Naive Bayes, iterative Naive Bayes, linear regression, logistic regression, SVM, decision tree, and random forest and clustering using k-means and fuzzy k-means.

Strong points

• General purpose, wide set of algorithms with learning schemes, models and algorithms from Weka and R scripts.
• Add-ons supports with selected algorithms for large-scale data.
• Strong community, well support, cross-platform framework.

Weak points

• Proprietary product for large problem solutions.

Return to Contemt