Application of Dimensionality Reduction in Recommender System - A Case Study

@inproceedings{Sarwar2000ApplicationOD,
  title={Application of Dimensionality Reduction in Recommender System - A Case Study},
  author={Badrul Munir Sarwar and George Karypis and Joseph A. Konstan and John Riedl},
  year={2000}
}
Abstract : We investigate the use of dimensionality reduction to improve performance for a new class of data analysis software called "recommender systems" Recommender systems apply knowledge discovery techniques to the problem of making product recommendations during a live customer interaction. [...] Key Result Collaborative filtering has been shown to produce high quality recommendations, but the performance degrades with the number of customers and products. New recommender system technologies are needed…Expand
Incremental Singular Value Decomposition Algorithms for Highly Scalable Recommender Systems
We investigate the use of dimensionality reduction to improve the performance for a new class of data analysis software called “recommender systems”. Recommender systems apply knowledge discoveryExpand
A Study of Recommender System Techniques
TLDR
Recommender systems are useful in predicting the helpfulness of controversial reviews and are intelligent applications to assist users in a decision-making process where they want to choose one item amongst a potentially overwhelming set of alternative products or services. Expand
Simulation Study on E-commerce Recommender System Based on a Customer-Product Purchase-Matrix
TLDR
Simulation experiments on synthetic transaction data show SVD-based recommender system yields a better performance than the CF method and reduced product dimensionality from SVD may be more effective in generating a reliable neighborhood than CF method, and thereby it may improve the efficiency of recommendation performance. Expand
Recommender Systems for Social Networks Analysis and Mining: Precision Versus Diversity
TLDR
The diversity-accuracy challenge in recommender systems is introduced, and two recommendation algorithms which approach the problem from two perspectives are presented which resolves the dilemma and provides adjustable level of accuracy and diversity that can be tuned by a single parameter. Expand
A new recommendation algorithm for reducing dimensionality and improving accuracy
TLDR
A new algorithm is described that represents a solution to overcome the problem of high dimensionality when using matrix factorization for recommendation and significantly improves the accuracy of recommender systems over existing approaches. Expand
Robust, scalable, and practical algorithms for recommender systems
TLDR
This thesis proposes a novel switching hybrid recommendation framework that combines Collaborative Filtering (CF) with a content-based filtering algorithm and proposes a new class of kernel mapping recommender system methods that are called KMR for solving the recommendation problem. Expand
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. Expand
A personalised recommendation procedure based on dimensionality reduction and web mining
TLDR
This paper proposes hybrid recommendation methodologies based on web usage mining and dimensionality reduction techniques to enhance the recommendation quality and performance of current collaborative filtering-based recommender systems. Expand
Information enrichment for quality recommender systems
TLDR
A novel and intuitive approach towards improving recommendation quality and alleviating the cold-start problem is attempted, and a taxonomy-based recommender, Hybrid Taxonomy Recommender (HTR), is presented in this thesis. Expand
Scalable Recommendations Using Clustering Based Collaborative Filtering
TLDR
This work first partition the set of users using a CURE (Clustering using representatives) based method and then leverage the resultant clusters to formulate recommendations for the target user, resulting in reduced recommendation time. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 32 REFERENCES
Applying Knowledge from KDD to Recommender Systems
TLDR
This work investigates a new class of software for knowledge discovery in databases, called recommender systems, which apply KDD-like techniques to the problem of making product recommendations during a live customer interaction and explores one technology called Singular Value Decomposition (SVD) to reduce the dimensionality of recommender system problems. Expand
Using filtering agents to improve prediction quality in the GroupLens research collaborative filtering system
TLDR
The filterbot model allows collaborative filtering systems to address sparsity by tapping the strength of content filtering techniques and is experimentally validated by showing that even simple filterbots such as spell checking can increase the utility for users of sparsely populated collaborative filtering system. Expand
Learning Collaborative Information Filters
TLDR
This work proposes a representation for collaborative filtering tasks that allows the application of virtually any machine learning algorithm, and identifies the shortcomings of current collaborative filtering techniques and proposes the use of learning algorithms paired with feature extraction techniques that specifically address the limitations of previous approaches. Expand
Combining Collaborative Filtering with Personal Agents for Better Recommendations
TLDR
This paper shows that a CF framework can be used to combine personal IF agents and the opinions of a community of users to produce better recommendations than either agents or users can produce alone. Expand
Social information filtering: algorithms for automating “word of mouth”
TLDR
The implementation of a networked system called Ringo, which makes personalized recommendations for music albums and artists, and four different algorithms for making recommendations by using social information filtering were tested and compared. Expand
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. Expand
Data Mining for Direct Marketing: Problems and Solutions
TLDR
This paper discusses methods of coping with problems during data mining based on the experience on direct-marketing projects using data mining, and suggests a simple yet effective way of evaluating learning methods. Expand
Knowledge = concepts: a harmful equation
Research on knowledge discovery in databases (KDD) has been impeded by a limited vision of knowledge, inherited from machine learning (ML) and other branches of computer science. In contrast with KDDExpand
Mining business databases
TLDR
The goal here is to provide a brief overview of the key issues in knowledge discovery in an industrial context and outline representative applications. Expand
Direct Marketing Response Models Using Genetic Algorithms
TLDR
A genetic algorithm based approach for developing response models aimed at maximizing performance at the desired mailing depth and fit-to-data, and tradeoffs amongst these empirically explored are explored. Expand
...
1
2
3
4
...