Increasing Recommendation Accuracy and Diversity via Social Networks Hyperbolic Embedding

Several applications are built around sharing information by leveraging social network connections. For example, in social buying sites like Groupon, a deal is usually forwarded to interested recipients through their social graph. A primary goal is to improve user satisfaction by maximizing the relevance of the shared message to the target audience. The more personalized products or offers you promote to the users the greater is the chance to attract them and increase your revenues. To create more personalized products, one should consider not only offering accurate recommendations but also diverse, since diversity plays an important factor and should not be disregarded. In this work, we address this problem by proposing a social network hyperbolic embedding that exploits both social connections and user preferences aiming at enhancing the relevance of recommendations and increasing their diversity and accuracy by ensuring that each message will be delivered to the most interested users.