I am new to Machine learning and trying to learn by practicing.

I have a situation where I am reading a set of N data. Each of N data will have independent state at any moment of time. I want to use these N data to find a relation between them. In case if I am not receiving one or more sets of data, I should be able to use available relation between N data to predict the missing data.

What type of machine learning algorithm can be used?


I understand your task can be formulated as an imputation task, see the link below for further details. Also before you proceed look up the concepts of missing data.

In order to fill in missing data you’ll have to build N distinct models using available observations. Each of N models will have N-1 inputs.

Note that because more than one component can be missing your models should be able to handle the missing data. According to my knowledge neural networks cannot handle the missing data out of the box. Tree based models, such that random forests or GBMs are more suitable for this kind of tasks.


| improve this answer | |
  • $\begingroup$ thanks for the reply. Let me go through the link to understand this concept. $\endgroup$ – 0x07FC Mar 27 '18 at 8:09

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.