I am trying to train an LSTM(many to one) model with multivariate time series input and a categorical output.

after training for quite some time, the resulting model still has low accuracy and high loss on validation data. So started doubting that maybe the features I had chosen for predicting the label are simply irrelevant?

I wonder if there are methods for testing if the chosen features do have explanatory power on labels?

Before coming to stack exchange, I did some research online and found somebody saying we should be using PCA to test if labels are dependent on features, which confused me a lot. I thought PCA is used for dimension reduction on features and is irrelevant to labels. am I missing something here?

Below is an extract of what I just mentioned.

  1. It is always a good idea first to make sure that the output (dependent) variable (target or label) actually depends on the input variables (features). It is possible that you are chasing a ghost that doesn’t exist. There is a way to check this, but before that, we have step two.
  2. Start by using the z-scores to normalize the input variables. Any normalizing would do but there is a reason for using z-scores. It has to do with the next step. You can do a Principal Component Analysis (PCA). It will tell you the contribution of each of the new variables (obtained after the transformation) to the variation on the output variable.
  3. PCA will answer the question I mentioned at the outset about the existence of dependency clearly. Before performing PCA, the variables have to be normalized using z-scores.

source of the above extract

  • $\begingroup$ Related $\endgroup$
    – Dave
    Oct 3, 2023 at 2:55

1 Answer 1


One quick way (if they are numerical and not categorical data) would be to create a correlation heatmap (like this library implements) and observe if any of the cells are particularly correlated with your label column. Of course, this is not a completely definitive method, because sometimes the correlations can span between columns, but it's worth a try. Here is a good tutorial


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.