> ## Documentation Index
> Fetch the complete documentation index at: https://kumo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# lag_timesteps

#### `lag_timesteps: <integer>` (Optional)

## Description

For forecasting problems, leverage the auto-regressive labels as inputs. This parameter controls the number of previous values should be considered as auto-regressive labels.

### Supported Task Types

* Forecasting

### Example

For the following query, a value of `lag_timesteps=3` will consider sum from the last 3, 7-day, windows as input features.

<CodeGroup>
  ```yaml Field theme={null}
  PREDICT SUM(TRANSACTIONS.AMOUNT, 0, 7, days)
  FOR EACH CUSTOMERS.CUSTOMER_ID
  ```
</CodeGroup>

### Default Values

| run\_mode | Default Value |
| :-------- | :------------ |
| FAST      | `1`           |
| NORMAL    | `1`           |
| BEST      | `1`           |

<Warning>
  Experimental Feature
</Warning>