Store Match Node
The Store Match node finds the best match across each Family of Products sold by the Brand’s Master Distributor. The Brand’s Master Distributor Products are matched to the subset of Products sold by each of the other Stores.
The final Product matches are set in the Family column in the Output Product Array. A downstream Similarity Collapse node can then be used to collapse all of the matched Products together. This allows the user to eliminate the Stores from the analysis and simulate the Market based upon just the collapsed Products.
The Store Match node finds the best match across each Family of Products sold by the Brand’s Master Distributor. The Matching Algorithm relies heavily upon text-matching within the Description, but the Correlation can also be used if the Input Similarity Rankings are provided.
Input Product Array
The super-set of Products from which the smaller set of matched Product Families will be defined. Each row corresponds to a Product that is to be compared with the Master Distributor.
Product Similarity Rankings
The optional list of all Product-to-Product rankings. That is, from the Customers who looked at Product01 how did they rank Product02. Alternatively, from the Customers who looked at Product01 what is the probability that they also looked at Product02 (sorted to provide a rank order).
If the optional ‘Input Product Similarity Rankings’ is missing then Product Correlations are ignored and matches are based upon the Description text.
The Focus Product determines the Master Distributor for the Brands sold by the Focus Store. The Focus Product should be found in both the Input Product Array and the Input Product Similarity Rankings. If the Focus Product is not set then the Store which carries the widest range of Products is set to be the Master Distributor.
Extra weight can be given to similar Product Attributes. For example, the Description Similarity Weight is the weight given to the similarity between the Descriptions of the two Products being compared by the Store Match algorithm. The greater the value, the more weight is given to Product Descriptions being nearly identical.