Merge pull request #89268 from trevorbye/master

more info/guidance on forecast params

Author: PRMerger16

articles/machine-learning/service/how-to-auto-train-forecast.md

@@ -95,8 +95,10 @@ The `AutoMLConfig` object defines the settings and data necessary for an automat
 |`time_column_name`|Used to specify the datetime column in the input data used for building the time series and inferring its frequency.|✓|
 |`grain_column_names`|Name(s) defining individual series groups in the input data. If grain is not defined, the data set is assumed to be one time-series.||
 |`max_horizon`|Defines the maximum desired forecast horizon in units of time-series frequency. Units are based on the time interval of your training data, e.g. monthly, weekly that the forecaster should predict out.|✓|
-|`target_lags`|Number of rows to lag the target values based on the frequency of the data. This is represented as a list or single integer.||
-|`target_rolling_window_size`|*n* historical periods to use to generate forecasted values, <= training set size. If omitted, *n* is the full training set size.||
+|`target_lags`|Number of rows to lag the target values based on the frequency of the data. This is represented as a list or single integer. Lag should be used when the relationship between the independent variables and dependant variable do not match up or correlate by default. For example, when trying to forecast demand for a product, the demand in any month may depend on the price of specific commodities 3 months prior. In this example, you may want to lag the target (demand) negatively by 3 months so that the model is training on the correct relationship.||
+|`target_rolling_window_size`|*n* historical periods to use to generate forecasted values, <= training set size. If omitted, *n* is the full training set size. Specify this parameter when you only want to consider a certain amount of history when training the model.||
+
+See the [reference documentation](https://docs.microsoft.com/python/api/azureml-train-automl/azureml.train.automl.automlconfig?view=azure-ml-py) for more information.
 
 Create the time-series settings as a dictionary object. Set the `time_column_name` to the `day_datetime` field in the data set. Define the `grain_column_names` parameter to ensure that **two separate time-series groups** are created for the data; one for store A and B. Lastly, set the `max_horizon` to 50 in order to predict for the entire test set. Set a forecast window to 10 periods with `target_rolling_window_size`, and specify a single lag on the target values for 2 periods ahead with the `target_lags` parameter.