Empirical Analysis of Predictive Algorithms for Collaborative Filtering

Abstract

Collaborative filtering or recommender systems use a database about user preferences to predict additional topics or products a new user might like. In this paper we describe several algorithms designed for this task, including techniques based on correlation coefficients, vector-based similarity calculations, and statistical Bayesian methods. We compare the predictive accuracy of the various methods in a set of representative problem domains. We use two basic classes of evaluation metrics. The first characterizes accuracy over a set of individual predictions in terms of average absolute deviation. The second estimates the utility of a ranked list of suggested items. This metric uses an estimate of the probability that a user will see a recommendation in an ordered list. Experiments were run for datasets associated with 3 application areas, 4 experimental protocols, and the 2 evaluation metrics for the various algorithms. Results indicate that for a wide range of conditions, Bayesian networks with decision trees at each node and correlation methods outperform Bayesian-clustering and vector-similarity methods. Between correlation and Bayesian networks, the preferred method depends on the nature of the dataset, nature of the application (ranked versus one-by-one presentation), and the availability of votes with which to make predictions. Other considerations include the size of database, speed of predictions, and learning time.

Appears in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998)

References in corpus (2)

• A Bayesian Approach to Learning Bayesian Networks with Local Structure
• Learning Mixtures of DAG Models

Cited by in corpus (130)

• From Frequency to Meaning: Vector Space Models of Semantics
• Recommender Systems
• Collaborative Filtering by Personality Diagnosis: A Hybrid Memory- and Model-Based Approach
• Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments
• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• Beyond Personalization: Research Directions in Multistakeholder Recommendation
• Attention-Sensitive Alerting
• A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization
• Collaborative Filtering and the Missing at Random Assumption
• Coupling Learning of Complex Interactions
• Using Temporal Data for Making Recommendations
• Recommender System for Online Dating Service
• On the Dimensionality of Word Embedding
• Deep Reinforcement Learning for List-wise Recommendations
• An MDP-based Recommender System
• Multi-Domain Collaborative Filtering
• A probabilistic model to resolve diversity-accuracy challenge of recommendation systems
• Direct Optimization of Ranking Measures
• Nonparametric Density Estimation for High-Dimensional Data - Algorithms and Applications
• Collaborative Ensemble Learning: Combining Collaborative and Content-Based Information Filtering via Hierarchical Bayes
• Preference-based Graphic Models for Collaborative Filtering
• Recommender Systems for Online and Mobile Social Networks: A survey
• Training Deep AutoEncoders for Collaborative Filtering
• RecSim: A Configurable Simulation Platform for Recommender Systems
• A Machine-Learning Item Recommendation System for Video Games
• Effective Mechanism for Social Recommendation of News
• Personalizing Image Search Results on Flickr
• Sequential Selection of Correlated Ads by POMDPs
• Information Filtering via Collaborative User Clustering Modeling
• A multi-theoretical kernel-based approach to social network-based recommendation
• Recommender systems based on graph embedding techniques: A comprehensive review
• Bayesian hierarchical rule modeling for predicting medical conditions
• A Recommender System based on Idiotypic Artificial Immune Networks
• A difficulty ranking approach to personalization in E-learning
• Maximizing profit using recommender systems
• Exploring an opinion network for taste prediction: an empirical study
• Time-Aware Music Recommender Systems: Modeling the Evolution of Implicit User Preferences and User Listening Habits in A Collaborative Filtering Approach
• Client-server multi-task learning from distributed datasets
• Evaluation of recommender systems in streaming environments
• Personalized Academic Research Paper Recommendation System
• Exploiting the Structure of Bipartite Graphs for Algebraic and Spectral Graph Theory Applications
• Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology
• Profiling vs. Time vs. Content: What does Matter for Top-k Publication Recommendation based on Twitter Profiles? - An Extended Technical Report
• Dependency Networks for Collaborative Filtering and Data Visualization
• Advances in Machine Learning for the Behavioral Sciences
• Top-N Recommender System via Matrix Completion
• Collaborative Personalized Web Recommender System using Entropy based Similarity Measure
• Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications
• Recommender Systems by means of Information Retrieval
• Memory-efficient Embedding for Recommendations
• Statistical analysis of $k$-nearest neighbor collaborative recommendation
• Social Collaborative Retrieval
• Information Filtering on Coupled Social Networks
• Learning Tensors in Reproducing Kernel Hilbert Spaces with Multilinear Spectral Penalties
• A Connection-Centric Survey of Recommender Systems Research
• Individualized Rank Aggregation using Nuclear Norm Regularization
• The FacT: Taming Latent Factor Models for Explainability with Factorization Trees
• Explainable Recommendation: Theory and Applications
• Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time
• Response Aware Model-Based Collaborative Filtering
• RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
• An Efficient Approach to Informative Feature Extraction from Multimodal Data
• Patient similarity: methods and applications
• Modeling item--item similarities for personalized recommendations on Yahoo! front page
• B-Rank: A top N Recommendation Algorithm
• Convolutional Geometric Matrix Completion
• Combining configuration and recommendation to define an interactive product line configuration approach
• A Hybrid Approach to Web Service Recommendation Based on QoS-Aware Rating and Ranking
• A Bayesian non-parametric method for clustering high-dimensional binary data
• Mobile Recommender Systems Methods: An Overview
• Assessing the Impact of a User-Item Collaborative Attack on Class of Users
• Selecting Reliable Blockchain Peers via Hybrid Blockchain Reliability Prediction
• A Harmonic Extension Approach for Collaborative Ranking
• Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
• CFW: A Collaborative Filtering System Using Posteriors Over Weights Of Evidence
• Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness
• Evaluating Recommendation Algorithms by Graph Analysis
• An Investigation on Social Network Recommender Systems and Collaborative Filtering Techniques
• Research Progress of News Recommendation Methods
• A Comprehensive Review on Non-Neural Networks Collaborative Filtering Recommendation Systems
• Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context
• Ordinal Boltzmann Machines for Collaborative Filtering
• iTrace: An Implicit Trust Inference Method for Trust-aware Collaborative Filtering
• Using content features to enhance performance of user-based collaborative filtering performance of user-based collaborative filtering
• Finding the Right Set of Users: Generalized Constraints for Group Recommendations
• When are recommender systems useful?
• Applying machine learning techniques to improve user acceptance on ubiquitous environement
• CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation
• Future-Aware Diverse Trends Framework for Recommendation
• Emergence of Spontaneous Order Through Neighborhood Formation in Peer-to-Peer Recommender Systems
• Recommendation systems in the scope of opinion formation: a model
• Improving adaptation of ubiquitous recommander systems by using reinforcement learning and collaborative filtering
• A Stochastic Model for Collaborative Recommendation
• A Collaborative Filtering Based Approach for Recommending Elective Courses
• Survey of Privacy-Preserving Collaborative Filtering
• The Graph-Based Behavior-Aware Recommendation for Interactive News
• A Deep, Forgetful Novelty-Seeking Movie Recommender Model
• ModelWizard: Toward Interactive Model Construction
• When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution
• Location histogram privacy by sensitive location hiding and target histogram avoidance/resemblance (extended version)
• Construction of Community Web Directories based on Web usage Data
• Combining Privileged Information to Improve Context-Aware Recommender Systems
• MedTQ: Dynamic Topic Discovery and Query Generation for Medical Ontologies
• Achieve Better Ranking Accuracy Using CloudRank Framework for Cloud Services
• Measuring Similarity between Brands using Followers' Post in Social Media
• Learning Distributional Programs for Relational Autocompletion
• Advances in Collaborative Filtering and Ranking
• Hybrid Q-Learning Applied to Ubiquitous recommender system
• A Probabilistic Generative Model of Linguistic Typology
• Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction
• PNP: Fast Path Ensemble Method for Movie Design
• Risk Aware Ranking for Top-$k$ Recommendations
• A hybrid recommendation algorithm based on weighted stochastic block model
• Exploiting Hierarchy for Ranking-based Recommendation
• Benchmarking Surrogate-Assisted Genetic Recommender Systems
• Collaborative Self-Attention for Recommender Systems
• Parallel Matrix Factorization for Binary Response
• Sequential Relevance Maximization with Binary Feedback
• NU:BRIEF -- A Privacy-aware Newsletter Personalization Engine for Publishers
• Context-Specific Likelihood Weighting
• On Content-Based Recommendation and User Privacy in Social-Tagging Systems
• FES: A Fast Efficient Scalable QoS Prediction Framework
• Deep Latent Factor Model for Collaborative Filtering
• PMD: An Optimal Transportation-based User Distance for Recommender Systems
• A Recommender System based on the Immune Network
• Preference Modeling by Exploiting Latent Components of Ratings
• The Latent Bernoulli-Gauss Model for Data Analysis
• Cluster Developing 1-Bit Matrix Completion
• Outlier-Resilient Web Service QoS Prediction