I want to apply a predictive ranking algorithm to a dataset, so I've been reading about Learning to Rank, RankNet and LambdaMART [1][2].

These methods use neural nets or trees as their core framework. I'm wondering if there are any simpler methodologies available i.e. the linear regression (OLS) for predictive ranking?


1 Answer 1


The most appropriate variation of regression is ordinal regression. Ordinal regression tends to not perform well because of the complexity and sparseness of most ranking problems.

Almost all supervised learning algorithms have a learning to rank variation. Typically, learning to rank problems involve text so algorithms that work well with text. Ranking support vector machines (SVM) was a popular choice before the deep learning revolution.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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