This is repository code of paper "Enhancing Multi-Output Time Series Forecasting with Encoder-Decoder Networks"

Predicted Spanish day-ahead energy demand and price with 97.5% accuracy using a range of ML and statistical time series forecasting models including XGBoost, Transformers, TFTs and SARIMA.

Designed as a training document explaining how to apply the multi-output method in time series forecasting. This means a single model can simultaneously predict multiple future values. more stable results than the recursive method.

Deep Learning Models for Forecasting Multiphase Production Time Series Data