多変量時系列 GluonTS DeepAR TODOリスト

個人的メモ
随時追記しています

1

github.com

  • we can do transfer learning in forecasting.

4

github.com
将来の値が予測できない変数が多数ある時の方法

  • if you don't have future values you can transform your original features into something else, which you could then more easily set (instead of using the direct value). For example, instead of using sunlight directly, you could use the co-variate "absolute/relative change to yesterday".
  • another approach is to use mulit-variate forecasting techniques where you forecast everything jointly

5

github.com

  • We align timestamps. The idea is that all timestamps within the same range, are represented by the same value. In this case 2019-7-2 is aligned to 2019-06-27.

必要性がいまいち理解できないがそういうものらしい。

  • I think we should remove make_evaluation_predictions entirely for a better more understandable solution.

「make_evaluation_predictions」はなくなるらしい。
こちらで議論されている。