Challenging the Long Tail Recommendation

By Hongzhi Yin, Bin Cui, Jing Li, Junjie Yao, Cheng Chen. Proceedings of the VLDB Endowment, 2012

366 citations recorded by the source corpus.

The success of "infinite-inventory" retailers such as Amazon.com and Netflix has been largely attributed to a "long tail" phenomenon. Although the majority of their inventory is not in high demand, these niche products, unavailable at limited-inventory competitors, generate a significant fraction of total revenue in aggregate. In addition, tail product availability can boost head sales by offering consumers the convenience of "one-stop shopping" for both their mainstream and niche tastes. However, most of existing recommender systems, especially collaborative filter based methods, can not recommend tail products due to the data sparsity issue. It has been widely acknowledged that to recommend popular products is easier yet more trivial while to recommend long tail products adds more novelty yet it is also a more challenging task. In this paper, we propose a novel suite of graph-based algorithms for the long tail recommendation. We first represent user-item information with undirected edge-weighted graph and investigate the theoretical foundation of applying Hitting Time algorithm for long tail item recommendation. To improve recommendation diversity and accuracy, we extend Hitting Time and propose efficient Absorbing Time algorithm to help users find their favorite long tail items. Finally, we refine the Absorbing Time algorithm and propose two entropy-biased Absorbing Cost algorithms to distinguish the variation on different user-item rating pairs, which further enhances the effectiveness of long tail recommendation. Empirical experiments on two real life datasets show that our proposed algorithms are effective to recommend long tail items and outperform state-of-the-art recommendation techniques.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/8c3c12a442da9fd7b3112dd180331d3576a5b998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Robin D. Burke
2. Jie Lu
3. Bamshad Mobasher
4. Yaochu Jin
5. Hongzhi Yin

In Information Systems

1. Hongzhi Yin
2. Tong Chen
3. Bamshad Mobasher
4. Xin Xia
5. Junliang Yu
6. Jie Lu
7. Robin D. Burke
8. Li-zhen Cui

In Management Science and Operations Research

1. Robin D. Burke
2. Bamshad Mobasher
3. Himan Abdollahpouri
4. Hongzhi Yin
5. Bin Cui
6. Jie Lu
7. Ling Chen
8. Qian Zhang

Citations in the corpus

• Recommender Systems (2016, neutral): “Methods that are specifically designed for the long tail in recommender algorithms are discussed in [173, 463, 648].”
• XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation (2022, background): “We hypothesize that two issues cause this biased distribution: a fraction of items often account for most interactions in recommender systems [34], and the notorious over-smoothing problem [35] that makes embed-dings locally similar, thus aggravating the Matthew Effect.”
• Artificial intelligence in recommender systems (2020, background): “When exploited, however, long-tail items can bring huge benefits to both customers and companies [205].”
• Feedback Loop and Bias Amplification in Recommender Systems (2020, background): “Recommendations generated by CF generally suffer from bias against certain groups of users or items [17, 18].”
• Self-Supervised Learning for Recommender Systems: A Survey (2022, neutral): “Meanwhile,recommendersystemsencounteruniquechallenges suchashighly-skeweddatadistribution[38],widelyobserved biases[39],andlarge-vocabularycategoricalfeatures[2],which providesoilfornew-typeSSLandhavespurredaseriesof distinctSSRmethodsthatcanenrichtheSSLfamily.”
• Managing Popularity Bias in Recommender Systems with Personalized Re-ranking (2019, methodology): “In order to evaluate the effectiveness of algorithms in mitigating popularity bias we use four different metrics: Average Recommendation Popularity (ARP): This measure from (Yin et al. 2012) calculates the average popularity of the recommended items in each list.”
• LCARS: a location-content-aware recommender system (2013, methodology): “To evaluate the recommender models, we adopt the testing methodology and the measurement Recall@k applied in [7, 5, 13, 32].”