The Demand Shredder node removes values from the Willingness To Pay (WTP) Matrix to reduce the possibility of Customers switching to unlikely Products outside of their normal Consideration Set.
Many Competitor Stores sell identical Products, and many Brands offer Products that are very similar. However Customers often do not consider these identical or highly similar Products, either because they are unaware of a Competitive Store's offering, or because they prefer not to investigate Brands they are unfamiliar with.
The Market Simulation Profit Engine assumes, by default, that all Customers are aware of all Product offerings. Therefore it allows a Virtual Customer to select perhaps their least favorite Product if only the Price of that Product were sufficiently discounted. However, this usually does not reflect the reality of the Market. A real-world Customer may never select a least favorite Product simply because they were not even aware of that Product's existence. A real-world Customer may only ever investigate the Product offerings from a single Store or a single Brand.
The Demand Shredder node can be configured, for example, so that Virtual Customers consider only their Top 3 to 4 Stores, their Top 2 to 5 Brands, and their Top 1 to 3 Locations. Demand Shredder Nodes can be chained together so that, in this example, the first node would be configured to shred less desirable Brands, the second node would be configured to shred less desirable Stores, and the third node would be configured to shred less desirable Locations.
In this way, the Demand Shredder node is able to model the 'Search Cost' a Customer would suffer if they were to do extensive research. Most Customers are prepared to forego an excellent deal if it means they can reduce the Search Cost required to identify such a deal. In other words, these Customers prefer a good deal with low Search Costs than the very best deal with high Search Costs.
The Demand Shredder node will always retain the Customer’s first Top Choice. The Top Choice is determined by maximizing the Consumer Surplus the Virtual Customer would receive across all Products in the Market. If the Demand Shredder is shredding Brands, then the Brand of the Customer’s top Product choice is always retained regardless of the Store, Location, or other Product Attribute. The advantage of retaining the Customer’s Top Choice is that the results of an upstream Tuning Algorithm should not be impacted by a Demand Shredder node. If, on the other hand, values were randomly shredded from the WTP Matrix, then a Profit Engine would yield different results between the shredded WTP Matrix and the original unshredded WTP Matrix.
Demand Shredder nodes are best located downstream a Market Simulation Tuning node after the final WTP Matrix values have already been calculated.
More Help: Examples and sample workflows can be found at the Scientific Strategy website: www.scientificstrategy.com.
Options
Standard Options
Advanced Options
Input Ports
- Input Product Array: The set of Products that define the Market. Each row corresponds to a Product that competes for Customers in the Market. The 'Product Array' must have the following columns:
- Product (string): The unique name of the Product corresponding to a column of the same name in the 'Input WTP Matrix'. There can also be an additional row with a Product named 'No Sale' - this row is used to handle those Customers who are in the Market but have not yet purchased a Product.
- Price (double): The Price of each Product in the Market. The Price of the Product is subtracted from each individual Customer's Willingness To Pay (WTP) to determine the Customer's remaining Consumer Surplus. The Customer's first Top Choice is the Product that has the greatest remaining Consumer Surplus. If the Price column is missing then the Customer's first Top Choice is the Product that has the greatest WTP. Otherwise, Products with missing Prices are deemed to be Out-of-Stock.
- Include (boolean): Set to TRUE to force a Product to always be included in the Consideration Set. This value is ignored unless the user selects the 'Always Include Consideration Set' to be 'Only Products marked Include' in the Advanced Options.
- Input Willingness To Pay Matrix (double): The set of Product-level Customer Distributions defining the Willingness To Pay (WTP) of each Product for each Virtual Customer in the Market. Each row corresponds to a Virtual Customer and contains the Customer's tuned Willingness To Pay (WTP). Each column corresponds to a Product. Each Product must have a corresponding entry in the 'Input Product Array'.
Output Ports
- Output Product Array: The Output Product Array is equivalent to the Input Product Array without any changes. The Product Array is simply passed through the node as a convenience to allow several of these 'Demand Shredder' nodes to be chained together.
- Output Willingness To Pay Matrix: The Output Willingness To Pay (WTP) Customer Distribution Matrix corresponds to the Input WTP Matrix. Certain WTP Values within the WTP Matrix will have been shredded where the Virtual Customer in each row would have been unlikely to have considered the Product in the value's column. Shredded values are replaced with '0.0'. The Output WTP Matrix is extended to contain these additional columns:
- Purchased: The name of the Product that would have been purchased by each Virtual Customer row according to their Willingness To Pay (WTP) for the Product and its Price. This Purchased Product is the Customer's first choice and will always be retained in the shredded Output WTP Matrix.
- Ranked Attributes: The comma-separated list of values for the user-selected Attribute in the order Ranked by each Virtual Customer row.
Views
- This node has no views
Workflows
CN-152 Demand Shredder Node v05KNIME Hub- KN-123 Data Generation for Market Basket Analysis v05KNIME Hub
- MS-173 Bertrand Competition with Search Costs v05KNIME Hub
Links
- No links available
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.