I have a set of continuous discrete values, which I would like to convert to a classification task. Say, my scores in an exam are anything between 0-100.

I want to convert my scores in the next exam prediction to a classification task. I do not want to predict the exact score. Instead, I want to predict which score bucket I would fall under. How do I decide the best score buckets to perform predictions so as to give a high accuracy? As in, how do I decide whether to choose the bucket (0-30,30-70,70-100) OR (0-40,40-80,80-100) OR (0-10,10-50,50-100)?

Which algorithms can I use for this purpose?

  • $\begingroup$ Ordinal logistic regression seems like a plausible place to start. $\endgroup$
    – Sycorax
    Oct 13, 2015 at 20:34

1 Answer 1


Use smbinning package and follow this method to adjust the bins : http://fr.mathworks.com/help/finance/case-study-for-a-credit-scorecard-analysis.html

  • 1
    $\begingroup$ Could you give a summary of the method described on the webpage you link to? If the link ever goes dead, your answer will be rendered useless. $\endgroup$ Oct 13, 2015 at 20:50
  • $\begingroup$ Welcome to Cross Validated! We are trying to build a permanent repository of high-quality statistical information in the form of questions & answers. We try to avoid link-only answers which the two previous comments point out the problems with.. As such this is more of a comment than an answer in its own right. If you're able, could you expand it into an answer that can stand on its own even if the link were no longer available, perhaps by giving a summary of the information at the link. Alternatively, we can convert it into a comment for you. $\endgroup$
    – Glen_b
    Oct 13, 2015 at 21:26

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.