• Corpus ID: 13470668

On the Gravity Recommendation System

@inproceedings{Takcs2007OnTG,
  title={On the Gravity Recommendation System},
  author={G{\'a}bor Tak{\'a}cs and Istv{\'a}n Pil{\'a}szy and Botty{\'a}n N{\'e}meth and Domonkos Tikk},
  year={2007}
}
The Netflix Prize is a collaborative filtering problem. This subfield of machine learning has become popular from the late 1990s with the spread of online services that use recommendation systems, such as e.g. Amazon, Yahoo! Music, and of course Netflix. The aim of such a system is to predict what items a user might like based on his/her and other users previous ratings. The dataset of Netflix Prize is much larger than the previously known benchmark sets, therefore we first show in the paper… 

Figures and Tables from this paper

Scalable Collaborative Filtering Approaches for Large Recommender Systems
TLDR
This work proposes various scalable solutions that are validated against the Netflix Prize data set, currently the largest publicly available collection of CF techniques, and proposes various matrix factorization (MF) based techniques.
Large-Scale Parallel Collaborative Filtering for the Netflix Prize
TLDR
This paper describes a CF algorithm alternating-least-squares with weighted-?-regularization(ALS-WR), which is implemented on a parallel Matlab platform and shows empirically that the performance of ALS-WR monotonically improves with both the number of features and thenumber of ALS iterations.
Matrix factorization and neighbor based algorithms for the netflix prize problem
TLDR
This work proposes various variants of matrix factorization (MF) and neighbor based approach (NB) that can boost the performance of the usual ensemble based scheme and investigates various regularization scenarios for MF.
Statistical Significance of the Netflix Challenge
TLDR
The goal is to address a statistical audience, and to provide a primarily statistical treatment of the lessons that have been learned from this remarkable set of data on collaborative filtering and recommender systems.
Collaborative Filtering for Recommender Systems
TLDR
A new prediction score model for the Memory-based method is proposed and a differential model that considers the adjustment process after the training process in the existing matrix factorization methods is proposed to avoid or compensate for the shortcomings of Matrix factorization and neighbor-based methods.
The BigChaos Solution to the Netflix Prize 2008
The team “BellKor in BigChaos” is a combined team of team BellKor and BigChaos. The solution with a RMSE of 0.8616 is created by a linear blend of the results from both teams. In the following paper
Evaluating Collaborative Filtering Recommender Algorithms: A Survey
TLDR
It is shown that there is no golden recommendation algorithm showing the best performance in all evaluation metrics, and that one should carefully consider the evaluation criteria in choosing a recommendation algorithm for a particular application.
Additive Regression Applied to a Large-Scale Collaborative Filtering Problem
  • Eibe Frank, M. Hall
  • Computer Science
    Australasian Conference on Artificial Intelligence
  • 2008
TLDR
This paper investigates the application of forward stage-wise additive modeling to the Netflix problem, using two regression schemes as base learners: ensembles of weighted simple linear regressors and k -means clustering--the latter being interpreted as a tool for multi-variate regression in this context.
Investigation of Various Matrix Factorization Methods for Large Recommender Systems
TLDR
An incremental variant of MF is described that efficiently handles new users/ratings, which is crucial in a real-life recommender system and a momentum-based MF approach is introduced that approximates the features by using positive values for either users or items.
A Matrix Factorization Algorithm for Efficient Recommendations in Social Rating Networks Using Constrained Optimization
TLDR
A matrix factorization algorithm is proposed that improves on previously proposed related approaches in terms of convergence speed, recommendation accuracy and performance on cold start users, and can be implemented easily, and thus used more frequently in social recommendation setups.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 17 REFERENCES
ClustKNN: A Highly Scalable Hybrid Model- & Memory-Based CF Algorithm
TLDR
This work proposes ClustKnn, a simple and intuitive algorithm that is well suited for large data sets and provides very good recommendation accuracy as well, and compares with a number of other popular CF algorithms that, apart from being highly scalable and intuitive, provide very good recommendations accuracy.
Application of Dimensionality Reduction in Recommender System - A Case Study
TLDR
This paper presents two different experiments where one technology called Singular Value Decomposition (SVD) is explored to reduce the dimensionality of recommender system databases and suggests that SVD has the potential to meet many of the challenges ofRecommender systems, under certain conditions.
Item-based collaborative filtering recommendation algorithms
TLDR
This paper analyzes item-based collaborative ltering techniques and suggests that item- based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.
The Netflix Prize
Netflix released a dataset containing 100 million anonymous movie ratings and challenged the data mining, machine learning and computer science communities to develop systems that could beat the
Empirical Analysis of Predictive Algorithms for Collaborative Filtering
TLDR
Several algorithms designed for collaborative filtering or recommender systems are described, including techniques based on correlation coefficients, vector-based similarity calculations, and statistical Bayesian methods, to compare the predictive accuracy of the various methods in a set of representative problem domains.
GroupLens: an open architecture for collaborative filtering of netnews
TLDR
GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles, and protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction.
Restricted Boltzmann machines for collaborative filtering
TLDR
This paper shows how a class of two-layer undirected graphical models, called Restricted Boltzmann Machines (RBM's), can be used to model tabular data, such as user's ratings of movies, and demonstrates that RBM's can be successfully applied to the Netflix data set.
Latent semantic models for collaborative filtering
TLDR
A new family of model-based algorithms designed for collaborative filtering rely on a statistical modelling technique that introduces latent class variables in a mixture model setting to discover user communities and prototypical interest profiles.
Collaborative filtering with privacy via factor analysis
TLDR
A new method for collaborative filtering which protects the privacy of individual data is described, based on a probabilistic factor analysis model, which has other advantages in speed and storage over previous algorithms.
Fast maximum margin matrix factorization for collaborative prediction
TLDR
This work investigates a direct gradient-based optimization method for MMMF and finds that MMMf substantially outperforms all nine methods he tested and demonstrates it on large collaborative prediction problems.
...
1
2
...