I have a dataset that consists of a target column with 65 classes. Also, the dataset has 200 columns/features. I researched multi-label classification and found the popular algorithms that can be used for multi-class classification include:

  • k-Nearest Neighbors
  • Decision Trees
  • Naive Bayes
  • Random Forest
  • Gradient Boosting etc.,

However, I saw multi-label classification examples that have four or five target categories.

Also from the Scikit-Learn Documentation on Multi-class:

Number of targets Target cardinality Valid type_of_target
Multiclass classification 1 >2 ‘multiclass’
Multilabel classification >1 2 (0 or 1) ‘multilabel-indicator’
Multiclass-multioutput classification >1 >2 ‘multiclass-multioutput’
Multioutput regression >1 Continuous ‘continuous-multioutput’

Found no maximum limit for cardinality in Multi-class. Is there any cardinality limit for Multi-class classification? Are there any popular algorithms that can be used for predicting the classes that contain more than 65 classes?


There is no hard limit on the number of classes. It depends on the specific problem and in other factors like the amount of data you have, regularization method etc.

There are many works that uses neural network, for example, to classify much more than 65 classes. Here is one article, out of many, that uses neural network and collaborative filtering techniques, to output classification probabilities for more than 20k different classes. https://arxiv.org/pdf/1802.05814.pdf


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.