Can ARIMA be multivariate?

In this blog post we’d like to show how Long Short Term Memories (LSTM) based RNNs can be used for multivariate time series forecasting by way of a bike sharing case study where we predict the demand for bikes based on multiple input features.

We see that the RMSE is quite low compared to the mean (11% of the size of the mean overall), which means that XGBoost did quite a good job at predicting the values of the test set .

A Multivariate Time Series consist of more than one time-dependent variable and each variable depends not only on its past values but also has some dependency on other variables .6 May 2021

ARIMAX is an extended version of the ARIMA model which utilizes multivariate time series forecasting using multiple time series which are provided as exogenous variables to forecast the dependent variable.