Clickstream Similarity Node
The Clickstream Similarity node converts a Clickstream Log File into a Product Similarity Rankings table that can be used by downstream nodes to generate a Product Correlation Matrix. For example, the Similarity Matrix node could be placed directly downstream of this Clickstream Similarity node.
The Clickstream Similarity node applies a modified ‘Markov Chain’ algorithm to calculate the probability that once the Customer views the If Product they will, at some point in the future, also view the Then Product. The algorithm puts greater weight on the Correlation Probability when the Then Product is viewed soon after the If Product. The algorithm also puts greater weight on those Products that the Customer views towards the end of their journey through the website, as opposed to those Products the Customer views at the beginning of their journey. These later Products are more likely to represent the Customer’s true interest than the earlier Products the Customer discovers when first entering the website.
The Clickstream Similarity node converts a Clickstream Log File into a Product Similarity Rankings table that can be used by downstream nodes to generate a Product Correlation Matrix. The Output Product Similarity Rankings table can then be used to generate a WTP Matrix containing the Willingness To Pay (WTP) of each Customer for each Product in a Market.
Lists the set of Customers who visited the website alongside the set of Products viewed by those Customers (listed in the order visited).
Optional detail concerning each Product found within the ‘Input Product Clickstream’.
The user can set the number of ranked ‘Then Products’ returned for each ‘If Product’ in the Output Product Similarity Rankings.