An easy way to Configure Recommendations
Recommendations are considered to be one of the key aspects of personalization. It provides customers with a far more relevant browsing experience, and allows marketers to create greater visibility to associated products or services .
Built over the unified customer stack, Plumb5 features a unique recommendation widget, which can recommend products to the browsing visitor, based on both individual and global parameters. This allows the marketer to recommend either based on context of the current session, or based on past data.
Recommendation pre-sets
Plumb5 offers recommendation pre-sets based on the following attributes
Based on Individual Attributes
Recommendations can be set based on individual attributes of the browsing visitor.
Based on User segment
Recommend products to the browsing visitor based on a particular user segment or for a particular score-range.
Based on Profile Segments
Recommend products based on user profile data.
Based on Product Views or Add to Cart events
Recommend products based on past behavior or interactions of a particular user group.
Based on Product category
Recommend product based on a particular product category or a particular product strategy.
Automating Recommendations
Recommendations can be automated using overall data to apply association rules to arrive at recommendations.
People who viewed this product also viewed (Based on Page Pattern)
Assign scores to data parameters and generate customer scorecards. Create customer segments across all data parameters.
People who purchased also purchased (Based on Purchase Pattern)
You can also enable the workflow to run the recommendation widget based on associated purchase views. Data used for this analysis includes all sessions where the selected product is purchased and the recommendation can be either of products purchased or products browsed.
Recommended for you (Based on customers within a segment who bought the same product also bought)
For cross-selling campaigns, You can also run a workflow to recommend products, by looking at other customers within a particular segment. This allows the marketer to fine tune recommendations based on lot of similar parameters, which can be optimize recommendation click-throughs.