I have a dataset containing reports of events in a company when something occurred. The report have:

  • Text description of the event
  • Code classification of the event
  • Date of the event

The code classification is for example HR for something happen with Human Resource service.

Now, I would like to predict what will be the next event based on the preceding events (text & code). Ex : if I have reports from 01/01/19 to 01/04/19, what is the most likely event to happen in the following days ?

Simple schema : enter image description here

I think there could be some patterns in the events or in text that could lead to predict the next event, but I’m a bit confused about all method that exist, especially LSTM which I think could be used in this case, but not really sure.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.