Predict the values of variable features over timestamps

Question

I have a dataset which contains timestamps and number of users at that timestamp. Each user has resource values which change per timestamp. How can I predict the number of users incoming at timestamp and the resource values of each user at that timestamp?

I found out that meta-learning model can be used for this proposal. Is there any conv Net or Deep neural networks can solve this proposal?

Answer 1

You can use recurrent neural networks, as well as ARIMA and SARIMA forecasting models for time series applications.

Here is a great tutorial provided by Jason Brownlee on using LSTM RNN models link.