Forecast
Last updated: 13 Jan 2023
Description¶
The Forecast node applies a forecast model to a data set.
Configuration Options¶
Basic Configuration Options¶
| Setting | Description\Parameters |
|---|---|
Split Columns |
The selected columns split the data set over to build additional models. |
Target Column |
The column we are predicting. |
Sort By Columns |
Sort data rows by these columns. |
Outliers Column |
Column to set an outlier (0/1). |
Predictors |
The columns we are using to predict. |
Advanced Configuration Options¶
Model Options
| Setting | Description |
|---|---|
Model Type |
The model type. Options |
- Auto
- Seasonal Causal
Consider Linear Seasonality||
|Periodicity||
|Force Non-Negative Forecasts||
|Prune Weak Predictors||
|Include Linear Term|Must be included if no predictors are specified.|
|Standardize Predictors|Standardize predictors between 1 and 0.|
|Auto-lag Predictors||
|Fill Target Zeroes With||
Advanced Options
| Setting | Description |
|---|---|
Automatically Detect/Exclude Outliers |
|
Minimum MAPE Improvement for Outlier |
|
Seasonality Extraction Bandwidth |
Bandwidth is the fraction of all data points for calculating the localized regression used in smoothing (LOESS). Smaller numbers = less smoothing. |
Trend Smoothing Bandwidth |
Bandwidth is the fraction of all data points for calculating the localized regression used in smoothing (LOESS). Smaller numbers = less smoothing. |
Actions¶
| Action | Description |
|---|---|
Preview |
Once the node is configured, the combined result set can be previewed at any time. |