# [A Memory-Network Based Solution for Multivariate Time-Series Forecasting](https://arxiv.org/abs/1809.02105)

*2019, Association for the Advancement of Artificial Intelligence*
###### tags: `references`
implementation: https://github.com/Maple728/MTNet/blob/master/models/MTNet.py




* number of long term historical data (n)=7
* loss function: L1
* evaluation metric:
* univariate prediction: Root mean square error, Mean absolute percentage error
* multivariate prediction: Root relative squared error, Empirical Correlation Coefficient