Can Neural Network Toolbox's time series model use data that are observed with different time-lags?

Hi, I am thinking about using the Neural Network Toolbox for fitting a time-series neural network model as written the link below.

Neural Network Time-Series Prediction and Modeling https://www.mathworks.com/help/nnet/gs/neural-network-time-series-prediction-and-modeling.html

Regarding this, I have two questions. Thank you in advance for your time.

1. However, my data shows sometimes 2 months lags and 3 month lags (or sometimes 1 month lag). Can I use this raw data to fit a model? or Do I need an additional approach? What could it be?

2. My input variables might not be independent. Would that bring a problem? Is this model smart enough to consider all the dependencies by itself?

Answer 1

[Greg Heath]

1. There is no problem if you can interpolate the series at equidistant points.

2. Correlated inputs are not a problem unless you want to rank their their importance.

Hope this helps.

Thank you for formally accepting my answer

Greg