Recommender Systems from Multiple Perspectives

Zhe Wang; Chao Pu; Felice Wang

doi:10.1017/9781009447515.007

5 - Recommender Systems from Multiple Perspectives

Published online by Cambridge University Press: 08 May 2025

Zhe Wang ,

Chao Pu and

Felice Wang

Book contents

Get access

Summary

Building an effective recommender system requires more than just a strong model; it involves addressing a range of complex technical issues that contribute to the overall performance. This chapter explores recommender systems from seven distinct angles, covering feature selection, retrieval layer strategies, real-time performance optimization, scenario-based objective selection, model structure improvements based on user intent, the cold start problem, and the “exploration vs. exploitation” challenge. By understanding these critical aspects, machine learning engineers can develop robust recommender systems with comprehensive capabilities.

Keywords

feature selection retrieval real-time optimization optimization objective selection cold start problem exploration exploitation

Type: Chapter
Information: Deep Learning Recommender Systems , pp. 143 - 190

DOI: https://doi.org/10.1017/9781009447515.007 [Opens in a new window]

Publisher: Cambridge University Press

Print publication year: 2025

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Book purchase

Temporarily unavailable

References

Lin, Xiao. Dual averaging methods for regularized stochastic learning and online optimization. Journal of Machine Learning Research, 11, 2010: 2543–2596.Google Scholar

Mcmahan, H. Brendan, et al. Ad click prediction: A view from the trenches. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA, August 11–14, 2013.Google Scholar

Covington, Paul, Adams, Jay, Sargin, Emre. Deep neural networks for YouTube recommenders. Proceedings of the 10th ACM Conference on Recommender Systems, Boston, MA, USA, September 15–19, 2016.Google Scholar

Ma, Xiao, et al. Entire space multi-task model: An effective approach for estimating post-click conversion rate. The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA, July 8–12, 2018.Google Scholar

Jacobs, Robert A., Jordan, Michael I., Nowlan, Steven J., Hinton, Geoffrey E.. Adaptive mixtures of local experts. Neural Computations, 3, 1991: 79–87.Google Scholar PubMed

Ma, Jiaqi, Zhao, Zhe, Yi, Xinyang, Chen, Jilin, Hong, Lichan, Chi, Ed H.. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, August 19–23, 2018.CrossRef Google Scholar

Tang, Hongyan, Liu, Junning, Zhao, Ming, Gong, Xudong. Progressive layered extraction (PLE): A novel multi-task learning (MTL) model for personalized recommendations. Proceedings of the 14th ACM Conference on Recommender Systems, Brazil [virtual event], September 22–26, 2020.Google Scholar

Amat, Fernando, et al. Artwork personalization at Netflix. Proceedings of the 12th ACM Conference on Recommender Systems, Vancouver, BC, Canada, October 2–7, 2018.Google Scholar

Elahi, Mehdi, Ricci, Francesco, Rubens, Neil. A survey of active learning in collaborative filtering recommender systems. Computer Science Review, 20, 2016: 29–50.Google Scholar

Auer, Peter, Cesa-Bianchi, Nicolo, Fischer, Paul. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47(2–3), 2002: 235–256.Google Scholar

Chapelle, Olivier, Li, Lihong. An empirical evaluation of Thompson sampling. Advances in Neural Information Processing Systems, 24, 2011: 1872.Google Scholar

Li, Lihong, et al. A contextual-bandit approach to personalized news article recommender. Proceedings of the 19th International Conference on World Wide Web, Raleigh, NC, USA, April 26–30, 2010.CrossRef Google Scholar