What can we do if your dataset is too big or your model is too complex and training times are prohibitive on a traditional machine? What can we do if we want to deploy the model for real-time predictions? Could big data platforms help with our scaling problems?
Notice that big data platforms speed up training and deployment, but do not change the data science cycle or the machine learning algorithms.
The workflow shown in this video is located on the EXAMPLES server under: 50_Applications/28_Predicting_Departure_Delays/02_Scaling_Analytics_w_BigData50_Applications/28_Predicting_Departure_Delays/02_Scaling_Analytics_w_BigData*
* The link will open the workflow directly in KNIME Analytics Platform (requirements: Windows; KNIME Analytics Platform must be installed with the Installer version 3.2.0 or higher)
