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)

Cited by in corpus (29)

• From Frequency to Meaning: Vector Space Models of Semantics
• 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
• Attention-Sensitive Alerting
• A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization
• Collaborative Filtering and the Missing at Random Assumption
• Using Temporal Data for Making Recommendations
• Recommender System for Online Dating Service
• Direct Optimization of Ranking Measures
• Collaborative Ensemble Learning: Combining Collaborative and Content-Based Information Filtering via Hierarchical Bayes
• Preference-based Graphic Models for Collaborative Filtering
• Personalizing Image Search Results on Flickr
• Bayesian hierarchical rule modeling for predicting medical conditions
• Exploring an opinion network for taste prediction: an empirical study
• Maximizing profit using recommender systems
• Personalized Academic Research Paper Recommendation System
• Dependency Networks for Collaborative Filtering and Data Visualization
• Recommender Systems by means of Information Retrieval
• Statistical analysis of $k$-nearest neighbor collaborative recommendation
• A Connection-Centric Survey of Recommender Systems Research
• Response Aware Model-Based Collaborative Filtering
• Combining configuration and recommendation to define an interactive product line configuration approach
• When are recommender systems useful?
• Finding the Right Set of Users: Generalized Constraints for Group Recommendations
• Recommendation systems in the scope of opinion formation: a model
• Emergence of Spontaneous Order Through Neighborhood Formation in Peer-to-Peer Recommender Systems
• A Stochastic Model for Collaborative Recommendation
• Applying machine learning techniques to improve user acceptance on ubiquitous environement
• The Latent Bernoulli-Gauss Model for Data Analysis