Application Case 5.8 (Continued)
e-commerce environment, Allegro realized that it needed to create a new, highly personalized solution integrating predictive analytics and campaign management into a real-time recommendation system.
Allegro decided to apply Social Network Analysis (SNA) as the analytic methodology underlying its product recommendation system. SNA focuses on the relationships or links between nodes (individuals or products) in a network, rather than the nodes’ attributes as in traditional statistical methods. SNA was used to group similar products into communities based on their commonalities; then, communities were weighted based on visitor click paths, items placed in shopping carts, and purchases to create predictive attributes. The graph in Figure 5.15 displays a few of the product communities generated by Allegro using the KXEN’s InfiniteInsight Social product for social network analysis (SNA).
Statistical classification models were then built using KXEN InfiniteInsight Modeler to predict conversion propensity for each product based on these SNA product communities and individual customer attributes. These conversion propensity scores are then used by Allegro to define personalized offers presented to millions of Web site visitors in real time.
Some of the challenges Allegro faced applying social network analysis included:
• Need to build multiple networks, depending on the product group categories – Very large differences in the frequency distribution of particular products and their popularity (clicks, transactions)
• Automatic setting of optimal parameters, such as the minimum number of occurrences of items (support)
• Automation through scripting
• Overconnected products (best-sellers, megahub communities).
Implementing this solution also presented its own challenges, including:
•Different rule sets are produced per Web page placement
•Business owners decide appropriate weightings of rule sets for each type of placement / business strategy
•Building 160k rules every week
•Automatic conversion of social network analyses into rules and table-ization of rules
Results
As a result of implementing social network analysis in its automated real-time recommendation process, Allegro has seen a marked improvement in all areas.
Today Allegro offers 80 million personalized product recommendations daily, and its page views have increased by over 30 percent. But it’s in the numbers delivered by Allegro’s two most critical KPIs that the results are most obvious.
• Click-through rate (CTR) has increased by more than 500 percent as compared to ‘best seller’ rules.
• Conversion rates are up by a factor of over 40X.
1. How did Allegro significantly improve Clickthrough rates with Web analytics?
2. What were the challenges, the proposed solution, and the obtained results?