TimeSeriesTransformerLSTM

This projects an improved model for the prediction of the time series data from the aviation industry. The older model which has the implementations of the approaches i.e. ARIMA and Seq2Seq RNN is present in the Repo.

Our model is essentially a encoder and decoder model with a Transformer based encoder and a RNN based decoder. Our model on an average performs better then all the previous methods. More details are present in report.

Contributors

  • Shashwat Trivedi
  • Harsh Rangwani
  • Pradeep Jangid