​
start_time: <integer | str> (Optional)

​
Description

Defines the timestamp for the beginning of the training data or numerical offset from the most recent entry to use to generate training data labels. Unless a custom time unit is specified in the aggregation, this value is in days. This can be used to make sure the query only generates labels on data from the last start_time days. Regardless of this value, all data is used as an input to the model, but this value can help limit what labels are generated.
  • start_time needs to be <= 0 or the string format of a timestamp, i.e. ‘2024-04-01’

​
Supported Task Types

  • Temporal

​
Example

For example, you may want to only use training examples for customers that churned in the last year, but those customers may have 10 years of data that we will use for training the model. 
start_time: <integer | str>
start_time: -10 # Only train on data from the last 10 days
start_time: -365 # Only train on data from the last year
Start_time: ‘2024-04-01’ # Only train on data starting from ‘2024-04-01’
This only applies to temporal queries (queries that include a temporal aggregation such as SUM(TRANSACTIONS.AMOUNT, 0, 2, days)) The unit of this step is the same as the unit in the aggregation.

​
Default Values

run_modeDefault Value
FASTNone
NORMALNone
BESTNone