# Predict future event using text and class

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 :

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.