This workflow trains a number of data analytics models and automatically selects the best model to predict departure delays from a selected airport. Data is the airline dataset downloadable from: Departure delay is a delay > 15min. Default selected airport is ORD. This workflow implements data reading, ETL, outlier detection, dimensionality reduction, feature generation, feature selection, advanced data mining models, model selection and comparison.


This workflow uses airport and meteorlogical data to predict airline delays. It uses several open source integrations to both create simple visualizations of the data, and build models for delay prediction. It also compares the results of the various models. Execution of this workflow requires the following KNIME extensions: *KNIME H2O Machine Learning Integration *KNIME Python Integration. It also requires a configuration of Python 3.5 with pandas, scikit-learn, and matplotlib packages installed.

Subscribe to Predicting Departure Delays