CODEWITHSUNDEEP
machine-learningkerastime-serieslstm
A.Abs
A.Abs

Reputation: 470

LSTM multi-step prediction with a single time-signal input

Say I have one-minute data sample collected from soccer matches with six features. 1500 games to train and test the model.

I have implemented LSTM model for multiple feature forecast. I trained/tested the model with lag 5 and got a score of 91%. I.e make a prediction for minute 6.

My question is, given only the first-minute data, is it possible to make a prediction for the remaining 89 minutes of the game? (Of course, I will design a new model with input shape(1,6) and output (89,6)

So my input_shape=(1,1,6) which always looks [[0,0,a,b,0,0]] where a and b are unique and pre-determined for each match.

And the expected output will have shape=(89,6).

I really appreciate any suggestion.

Upvotes: 0

Views: 210

Answers (1)

anand_v.singh
anand_v.singh

Reputation: 2838

Yes it is possible to do that, the method to be used will be a slight variation of a method known as Sampling Novel sequences and it follows this model

Sampling Novel Sequence

What basically happens is that you use first minute to predict second minute, rather than randomly generating it, and use the generated result as the Input for the next step and thus you continue, remember, this is only for the sampling/predicting stage and not for generation step, I learned this from Andrew ng's deep learning course and this links to the video for same.

And I believe you can handle shapes and dimensions accordingly. If you have any doubts or difficulties, comment below.

Image source: medium.com

Upvotes: 1

Related Questions