0
$\begingroup$

I am currently working on a time series forecasting model with a dataset that does not have consistent timestamps i.e. one row every 60 seconds. Is it possible to train an accurate model with this dataset or do I need to fill in the missing instances?

Example data:

| datetime      | feature 0 | feature 1 | feature 2 | feature 3 | feature 4 |
| ------------- | --------- | --------- | --------- | --------- | --------- |
| 11.9.21 12:00 | 0,8       | 0         | 1,9       | 3,5       | 5,8       |
| 11.9.21 12:11 | 0,3       | 4,2       | 5,6       | 4,9       | 1,2       |
| 11.9.21 12:20 | 0,1       | 0,15      | 0         | 0,54      | 8,8       |
| 11.9.21 12:21 | 1,3       | 0,8       | 2,1       | 8,9       | 0         |
| 11.9.21 12:47 | 4,8       | 1,4       | 4,3       | 0         | 2,14      |
| 11.9.21 13:00 | 2,3       | 0,7       | 4,7       | 12,8      | 2,8       |
| 12.9.21 12:00 | 1,2       | 6,1       | 4,5       | 5,8       | 0,1       |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.