Recommender systems in industrial contexts

2012/03/20 by Frank Meyer, Meyer, Frank · 17 citations
Computer Science · #Algorithm #Artificial intelligence #Computer science #Context (archaeology) #Core (optical fiber) #Data Management and Algorithms #Data mining #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Information retrieval #Machine Learning and Data Classification #Machine learning #Recommender Systems and Techniques #Recommender system #Similarity (geometry) #State (computer science) #cs.IR

paper · pdf · doi:10.48550/arxiv.1203.4487

published in arXiv (Cornell University) (Cornell University) · version 3.30, May 2012

openalex publication_date 2012/03/20 · arxiv created 2012/05/14 · arxiv updated 2012/05/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This thesis consists of four parts: - An analysis of the core functions and the prerequisites for recommender systems in an industrial context: we identify four core functions for recommendation systems: Help do Decide, Help to Compare, Help to Explore, Help to Discover. The implementation of these functions has implications for the choices at the heart of algorithmic recommender systems. - A state of the art, which deals with the main techniques used in automated recommendation system: the two most commonly used algorithmic methods, the K-Nearest-Neighbor methods (KNN) and the fast factorization methods are detailed. The state of the art presents also purely content-based methods, hybridization techniques, and the classical performance metrics used to evaluate the recommender systems. This state of the art then gives an overview of several systems, both from academia and industry (Amazon, Google ...). - An analysis of the performances and implications of a recommendation system developed during this thesis: this system, Reperio, is a hybrid recommender engine using KNN methods. We study the performance of the KNN methods, including the impact of similarity functions used. Then we study the performance of the KNN method in critical uses cases in cold start situation. - A methodology for analyzing the performance of recommender systems in industrial context: this methodology assesses the added value of algorithmic strategies and recommendation systems according to its core functions.

Citations

• Navigation in a small world
• Probabilistic Latent Semantic Analysis
• Bayesian Network Classifiers
• Evaluating collaborative filtering recommender systems
• Emergence of scaling in random networks
• Mixing patterns in networks
• Assortative Mixing in Networks
• The anatomy of a large-scale hypertextual Web search engine
• Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments
• Collaborative Filtering by Personality Diagnosis: A Hybrid Memory- and Model-Based Approach
• The Structure and Function of Complex Networks
• A User-Oriented Approach to Music Information Retrieval
• Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
• Content-Based Book Recommending Using Learning for Text Categorization

Cited by

• Toward a New Protocol to Evaluate Recommender Systems

Related

• Toward a New Protocol to Evaluate Recommender Systems
• A Survey of Real-World Recommender Systems: Challenges, Constraints, and Industrial Perspectives
• Comparison of the Efficiency of Different Algorithms on Recommendation System Design: a Case Study
• A Survey Paper on Recommender Systems
• Methodologies for Improving Modern Industrial Recommender Systems