> For the complete documentation index, see [llms.txt](https://doc.verteego.com/verteego-doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.verteego.com/verteego-doc/pipelines/forecasting-pipelines/configuration/building-the-training-and-prediction-set/input_prediction_columns.md).

# input\_prediction\_columns

### Description

Lists the specific columns from the Prediction input file that should be included during the prediction process. If this list is left empty, the model will consider all available columns in the dataset. Specifying particular columns can streamline the prediction process, ensuring that the model only processes relevant data, which can be particularly useful for reducing complexity and improving performance in datasets with a large number of features.

### Steps impacted

<mark style="background-color:green;">prediction</mark>

### Example

```yaml
column_to_predict: qty

# Columns present in your test set. 
# If your dataset is constructed in your prediction resolution, then this block is not required
input_prediction_columns:
- receipt_date
- item_id
- pos_id
```