Real-time recommendations for user-item streams

Abstract

Recommender systems support users in finding items or users matching their individual preferences or interests. With the growing importance of social networks and the ubiquitous availability of internet connectivity, data streams become one of the most important information sources. Popular streamed data sources are micro blogging services (e.g. "twitter"), update messages in social networks, or articles on online news portals. Traditional recommender algorithms focus on large user-item matrixes applying complex algorithms (e.g. "factorization machines") for extracting the dominant knowledge and reducing the noise. In stream-based scenarios these algorithms cannot be applied due to tight time-constraints and limited resources. In this paper we present a framework optimized for providing recommendations based on streams. We analyze the user-item interaction stream for several online news portals and present the computed characteristics of these streams. Subsequently, we develop several different algorithms optimized for providing recommendations based on streams fulfilling the requirements according to quality, robustness, scalability, and tight time-constraints. We evaluate the algorithms and combine different algorithms in ensembles in order to handle the context-dependent user expectations. The evaluation results show that the developed algorithms outperform traditional recommender approaches and allow us to provide context-aware relevant recommendations.

Online Social Media Recommendation Over Streams

“…Chen et al [10] models users and items using competitive matrix factorization for temporal stream recommendation. Lommatzsch and Albayrak [21] apply the traditional collaborative filtering to the user interaction patterns within the recent time window. However, this technique is only applicable for items with strong temporal patterns, such as news articles.…”

“…However, existing diversity-based approaches handle the user preferences as static, which ignores the temporal evolution of social users' preference. Recent recommendation approaches have been proposed to capture the user preferences over streams [8], [9], [17], [21]. They mainly focus on how to extend the traditional recommendation techniques such as matrix factorization [15] to streaming environments by applying them to media data with the support of efficient stream processing.…”

Overview of NewsREEL’16: Multi-dimensional Evaluation of Real-Time Stream-Recommendation Algorithms

“…Chen et al [5] studied various algorithms for real-time bidding of online ads. Garcin et al [9] and Lommatzsch [16] focus on news recommendation. These approaches have in common that they are all evaluated in a live scenario, i.e., recommender algorithms have been benchmarked by performing A/B testing.…”

Experimental IR Meets Multilinguality, Multimodality, and Interaction

“…Chen et al [6] studied various algorithms for real-time bidding of online ads. Garcin et al [9] and Lommatzsch [20] focus on news recommendation, the latter in the context of the scenario presented by NewsREEL.…”

“…Based on contextual factors, the system picked the most promising algorithm from a set of existing recommenders. Team "abc" extends the approach of team "artificial intelligence" by considering trends with respect to success of individual recommenders [20]. The remaining participants have not yet revealed their approaches.…”