I’m very beginner, I’m trying to design a prediction model for forecasting the status one hour ahead.I have 150 sample data, each consisting of of 24 hours of time-series data with multiple features (5 time series features, represented as x), and labels (positive or negative, represented as y)

My question is how to design a model to predict the status one hour in advance (or the probability of that status). In other words, can I predict the status an hour before in advance ? I am considering using an LSTM model (Many-to-One model), but I have no idea how to design the model for predicting the status one hour before it occurs. I would like to know how to organize the dataset (its shape) for feeding it to the model.

I have a basic understanding of LSTM and experience in training with single time-series data.

I would greatly appreciate any of your brilliant ideas and advice to design it.

enter image description here



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.