I am developing a sequence-to-sequence LSTM model for multi-step time series forecasting. I have the basic model working, so now I need to drill down on which loss function and evaluation metrics to try. I was just using the pytorch Smooth_L1_Loss to start with, and some metrics for MSE. But I don't think these are necessarily the best.

The challenge is that there are so many papers out there with different specialized loss functions, and metrics, that it is a bit confusing to know where to start. I was hoping someone might be able to identify some good places to start.

Hyndman et al., generally suggest the MAPE, MASE, and SMAPE metrics, and I believe I can find these in the pytorch-forecasting package. I believe those are just evaluation metrics right. I need to find some better choices of loss functions, so that I can begin the trial-and-error process of choosing the one that performs the best.

Thanks for any suggestions.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.