Open studsttat opened 1 year ago
@studsttat The terminology surrounding multivariate forecasting is quite ambiguous in ML. Data scientists with a computer science background often refer to it as a global model that involves numerous time series but with a single dependent variable (target). On the other hand, those from statistical or econ backgrounds use the term for situations involving multiple dependent variables, as seen in models like VAR (Vector Autoregression). Regardless of the interpretation, there is a plan to implement both local multivariate time series forecasting and global models. However, due to time constraints, the implementation may not happen immediately but is intended to be pursued sometime in the future.
But there are some study who conduct multivariate time series that uses various machine learning methods. My example is the study of Mulaudzi and Ajoodha (2020) namely "Application of deep learning to forecast the South African unemployment rate: a multivariate approach".
Reference: Mulaudzi, R., & Ajoodha, R. (2020, December). Application of deep learning to forecast the South African unemployment rate: a multivariate approach. In 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) (pp. 1-6). IEEE.
My apologize for my selfish request. Your package really helps a lot to train various machine learning algorithms for time series based on caret library. May I request you an issue for a multivariate time series one?