I am tasked with creating a classifier that is able to predict whether an item will be returned. This is supposed to not only happen on the basis of an individual item, but on all other items within the same order. Since the number of items within an order is variable I will need a model that is able to deal with variable input lengths.

What I would like my model to do is the following: I have an order with n items, these n items are vectors of length m which consist of numerical values, categorical values and word embeddings. I would like the model to output a vector of length n as well, where the vector outputs the probability that these items are returned.

What are possible models that can perform this?



Your Answer

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