Information Filtering Algorithm
(Redirected from information filtering algorithm)
Jump to navigation
Jump to search
An Information Filtering Algorithm is a information processing algorithm that can be implemented by an information filtering system to solve an information filtering task).
- Context:
- It can range from being a Data-Driven Information Filtering Algorithm (such as a collaborative filtering algorithm) to being a Heuristic Information Filtering Algorithm.
- It can range from being a Global Item Recommendation Algorithm to being a Community Item Recommendation Algorithm (for a related users) to being a Personalized Item Recommendation Algorithm.
- It can range from being a Generic Item Recommendation Algorithm Pattern to being a Domain-Specific Item Recommendation Algorithm(e.g for products, for songs, for opponents, ...).
- It can allowing the incorporation of additional information such as implicit feedback, temporal effects, and/or confidence levels.
- Example(s):
- Counter-Example(s):
- a User Recommendation Algorithm.
- an Information Retrieval Algorithm, which also requires a query as input.
- See: Information Filtering Algorithm, Classification Algorithm.
References
2015
- (Wang et al., 2015) ⇒ Hao Wang, Naiyan Wang, and Dit-Yan Yeung. (2015). “Collaborative Deep Learning for Recommender Systems.” In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2015). ISBN:978-1-4503-3664-2 doi:10.1145/2783258.2783273
- QUOTE: … Existing methods for RS can roughly be categorized into three classes [6]: content-based methods, collaborative filtering (CF) based methods, and hybrid methods. Content-based methods [17] make use of user profiles or product descriptions for recommendation. CF-based methods [23, 27] use the past activities or preferences, such as user ratings on items, without using user or product content information. Hybrid methods [1, 18, 12] seek to get the best of both worlds by combining content-based and CF-based methods. …
2014
- (Barbieri et al., 2014) ⇒ Nicola Barbieri, Giuseppe Manco, and Ettore Ritacco. (2014). “Probabilistic Approaches to Recommendations.” In: Synthesis Lectures on Data Mining and Knowledge Discovery, 5(2).
2013
- (Bobadilla et al, 2013) ⇒ Jesús Bobadilla, Fernando Ortega, Antonio Hernando, and Abraham Gutiérrez. (2013). “Recommender Systems Survey.” In: Knowledge-based systems 46 (2013): 109-132.
- QUOTE: … Currently, these systems are incorporating social information. In the future, they will use implicit, local and personal information from the Internet of things. This article provides an overview of recommender systems as well as collaborative filtering methods and algorithms; …
2012
- (Smola, 2012a) ⇒ Alex Smola. (2012). “Recommender Systems.” In: SML: Scalable Machine Learning - STATISTICS 241B, COMPUTER SCIENCE C281B
- http://alex.smola.org/teaching/berkeley2012/slides/8_Recommender.pdf
- QUOTE:
- Neighborhood methods.
- User / movie similarity
- Iteration on graph
- Matrix Factorization.
- Ranking and Session Modeling.
- Features
- Latent dense (Bayesian Probabilistic Matrix Factorization)
- Latent sparse (Dirichlet process factorization)
- Coldstart problem (inferring features)
- Neighborhood methods.
2009
- (Koren et al., 2009) ⇒ Yehuda Koren, Robert Bell, and Chris Volinsky. (2009). “Matrix Factorization Techniques for Recommender Systems.” Computer 42, no. 8
- QUOTE: As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest-neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels.
2005a
- (Wei et al., 2005) ⇒ Yan Zheng Wei, Luc Moreau, and Nicholas R. Jennings. (2005). “A Market-based Approach to Recommender Systems.” In: ACM Transactions on Information Systems (TOIS), 23(3) doi:10.1145/1080343.1080344.