On the Differences between View-Based and Purchase-Based Recommender Systems

E-commerce platforms often use collaborative filtering (CF) algorithms to recommend products to consumers. What recommendations consumers receive and how they respond to the recommendations largely depend on the design of CF algorithms. However, extant empirical research on recommender systems primarily focuses on how the presence of recommendations affects product demand, without considering the underlying algorithm design. Leveraging a field experiment on a major e-commerce platform, we examine the differential impact of two widely used CF designs: view-also-view (VAV) and purchase-also-purchase (PAP). We find several striking differences between the impact of these two designs on individual products. First, VAV is about seven times more effective in generating additional product views than PAP, but only about twice more effective in generating sales due to a lower conversion rate. Second, VAV is more effective in increasing views for more expensive products, whereas PAP is more effective in increasing sales for cheaper products. Third, VAV is less effective in increasing the views but more effective in increasing the sales of products with higher purchase incidence rates (PIRs). At the aggregate level, we find that PAP generates more sales than VAV for products with low price or moderate PIRs, albeit VAV generates more sales than PAP overall. Our findings suggest that platforms may benefit from employing different CF designs for different types of products.