Icon

04_​Model_​Comparison

Workflow to compare forecast performances and execution times of classical time series models, machine learning models, and an LSTM model

Data Access Forecasts by different time series models- Random Forest (Regression)- Linear Regression- Seasonal Naive- Moving Average- SARIMA- LSTM NetworkThe forecast horizon is one week (168 values) Access pretrained models Access seed data Forecast Restore seasonality and trend to forecasts Evaluate forecasts How fast is each model? substuting missing values with average ofprevious and nextLSTM.h51. Random Forest2. Linear Regression3. Seasonal Naive4. Moving average5. SARIMA6. LSTMRandomForest.modelLinReg.pmmlseed.tableseed.table ImputingMissing Values Loop Deployment- LSTM Loop Deployment- Random Forest Loop Deployment -Linear Regression Loop Deployment- SARIMA Loop Deployment -Seasonal Naive Loop Deployment- Mean Keras NetworkReader Table View Timer Info Deployment data Restore seasonalityand trend Line plots Execution time Merge Variables Model Reader PMML Reader Table Reader Table Reader Joiner Data Access Forecasts by different time series models- Random Forest (Regression)- Linear Regression- Seasonal Naive- Moving Average- SARIMA- LSTM NetworkThe forecast horizon is one week (168 values) Access pretrained models Access seed data Forecast Restore seasonality and trend to forecasts Evaluate forecasts How fast is each model? substuting missing values with average ofprevious and nextLSTM.h51. Random Forest2. Linear Regression3. Seasonal Naive4. Moving average5. SARIMA6. LSTMRandomForest.modelLinReg.pmmlseed.tableseed.tableImputingMissing Values Loop Deployment- LSTM Loop Deployment- Random Forest Loop Deployment -Linear Regression Loop Deployment- SARIMA Loop Deployment -Seasonal Naive Loop Deployment- Mean Keras NetworkReader Table View Timer Info Deployment data Restore seasonalityand trend Line plots Execution time Merge Variables Model Reader PMML Reader Table Reader Table Reader Joiner

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Maarit Laukkanen
Created at: 2020-02-07
On NodePit since: 2020-06-05
Last update: 2024-04-18
Created with KNIME version: v4.6.2
Tags: forecasttime series

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!