Category: KNIME Nodes

KNIME shortcut to copy-and-paste the output table data, along with table headings, to Excel.

KNIME shortcut to add a Customer Distribution of a Constant Value with Quickforms and Wrapped Meta Nodes.

Generates Customer Profile sample data using advanced data generation techniques. All of the nodes used in this example come from KNIME. These nodes can be used as an alternative to the Market Simulation data generation capabilities.

Demonstrates how complicated and exotic Customer Distributions can be generated with Flow Variables. In this case, 7 Sub-Distributions are defined in a list and then generated one-by-one in a loop. Each Sub-Distribution is then concatenated together into a single Customer Distribution.

Demonstrates how to generate Shopping Basket data for Customers shopping at a supermarket. The supermarket offers 48 Products across 10 Categories. Ten-Thousand Shopping Baskets are generated containing between 2 and 15 Products each.

Demonstrates how to perform Market Basket Analysis using Borgelt’s Association Rule Learner. Analyzes 10,000 Customer Baskets from a supermarket with 48 Products across 10 Categories. Generates sub-Basket rules that can more accurately determine recommendations than simple Product-pairs. Selects the best recommendations that maximize supermarket Revenue.

Compares the Keras Layer Nodes against the DL Python nodes. Builds four models which attempt to predict future sales. Two models predict “Today’s Sales” (which are already known to the model). The other two models predict “Tomorrow’s Sales” which correlate to the sales from the same-day-last-week. Viewing the node weights show how the models identify the most useful inputs.

Provides a Neural Network solution to the Kaggle Store Item Demand Forecasting Challenge. Input contains 5 years of store-item sales data. Deep Learning models use both Keras Layer Nodes and DL Python Nodes. Output predicts the daily sales of 50 different items over the next two years.