ARIMA Predictor

Computes predictions from an estimated AutoRegressive Integrated Moving Average (ARIMA) model.

Two types of predictions are computed:
1. Forecast: forecast of the given time series h periods ahead.
2. In-Sample Prediction: generates prediction in the range of the training data.
%%00009* If Dynamic is enabled lagged predictions are used, otherwise lagged true values are used.
%%00009* Level setting determines whether in-sample differenced or original values are output. If no differencing in ARIMA model, this setting has no effect.

Note: This component requires a Python environment with StatsModels package installed. In this blog post we explain how to setup the KNIME Python extension:
https://www.knime.com/blog/setting-up-the-knime-python-extension-revisited-for-python-30-and-20

Python script is used due to performance reasons. KNIME Autoregressive integrated moving average (ARIMA) extension provides an alternative ARIMA Predictor node:
https://kni.me/e/5_ZZ3nif8tLRjGji

Required extensions:
KNIME Python Integration
(https://hub.knime.com/knime/extensions/org.knime.features.python2/latest)
KNIME Quick Forms
(https://hub.knime.com/knime/extensions/org.knime.features.js.quickforms/latest)

Options

Dynamic

Check this box to use in-sample predictions as lagged values. Otherwise use true values.

Number of periods to forecast

How many periods ahead should be forecasted.

Type

*Only affects models with a non-zero value for the "I" component.%%00010linear: linear prediction of the differenced time series.%%00010levels: predict the values of the original time series.

Nodes

• Python Predictor2 ×
• Boolean Configuration1 ×
• Component Input1 ×
• Component Output1 ×
• Empty Table Creator1 ×
• Show all 7 nodes

Extensions

• FeatureKNIME Data Generation
• FeatureKNIME Python 2 Integration (legacy)
• FeatureKNIME Quick Forms

Links

• No links available