12,095 Hits in 7.6 sec

Distributed collaborative filtering with singular ratings for large scale recommendation

Ruzhi Xu, Shuaiqiang Wang, Xuwei Zheng, Yinong Chen
2014 Journal of Systems and Software  
In this paper, we propose SingCF approach, which attempts to incorporate multiple singular ratings, in addition to dual ratings, to implement collaborative filtering, aiming at improving the recommendation  ...  Collaborative filtering (CF) is an effective technique addressing the information overloading problem, where each user is associated with a set of rating scores on a set of items.  ...  Our main contributions in this research include: (1) We proposed SingCF, a collaborative filtering algorithm that incorporates singular ratings for improvement in recommendation accuracy, where we firstly  ... 
doi:10.1016/j.jss.2014.04.045 fatcat:lqybzskph5dwrgdwoww6qnsydu

Role of Matrix Factorization Model in Collaborative Filtering Algorithm: A Survey [article]

Dheeraj kumar Bokde, Sheetal Girase, Debajyoti Mukhopadhyay
2015 arXiv   pre-print
Collaborative Filtering is currently most widely used approach to build Recommendation System.  ...  CF techniques uses the user behavior in form of user item ratings as their information source for prediction.  ...  CONCLUSION Collaborative Filtering (CF) algorithms are most commonly used in Recommendation System (RS). CF algorithms now a day face the problem with large dataset and sparseness in rating matrix.  ... 
arXiv:1503.07475v1 fatcat:oggskvfgv5eg5o4x7y4s2lfbl4

Scalable Realistic Recommendation Datasets through Fractal Expansions [article]

Francois Belletti, Karthik Lakshmanan, Walid Krichene, Yi-Fan Chen, John Anderson
2019 arXiv   pre-print
Recommender System research suffers currently from a disconnect between the size of academic data sets and the scale of industrial production systems.  ...  We adapt the Kronecker Graph Theory to user/item incidence matrices and show that the corresponding fractal expansions preserve the fat-tailed distributions of user engagements, item popularity and singular  ...  Less obvious statistical patterns can give rise to more challenging synthetic large-scale collaborative filtering problems. IV.  ... 
arXiv:1901.08910v3 fatcat:vu7ndp32gnhbfk45bzwzgh2vrq

An Item-Based Collaborative Filtering using Dimensionality Reduction Techniques on Mahout Framework [article]

Dheeraj kumar Bokde, Sheetal Girase, Debajyoti Mukhopadhyay
2015 arXiv   pre-print
Collaborative Filtering is the most widely used prediction technique in Recommendation System. Most of the current CF recommender systems maintains single criteria user rating in user item matrix.  ...  This gives birth to Multi Criteria Collaborative Filtering.  ...  Users use a 13-level rating scale (from A+ to F) for rating purpose. In the original dataset there are 257,317 rating, with 127,829 users and 8272 movies.  ... 
arXiv:1503.06562v1 fatcat:yumsgrtc7ncflcnjmkre2xbhsm

RSVD-based Dimensionality Reduction for RecommenderSystems

Michal Ciesielczyk, Andrzej Szwabe
2011 International Journal of Machine Learning and Computing  
We analyze the results of using collaborative filtering based on SVD, RI, Reflective Random Indexing (RRI) and Randomized Singular Value Decomposition (RSVD) from the perspective of selected algebraic  ...  Index Terms-dimensionality reduction, random indexing, recommender system, singular value decomposition.  ...  reduction method for collaborative filtering.  ... 
doi:10.7763/ijmlc.2011.v1.25 fatcat:dvirepcjljgy5nms7wo5hbx3cq

Parallelized Training of Restricted Boltzmann Machines Using Markov-Chain Monte Carlo Methods

Pei Yang, Srinivas Varadharajan, Lucas A. Wilson, Don D. Smith, John A. Lockman, Vineet Gundecha, Quy Ta
2020 SN Computer Science  
Restricted Boltzmann machine (RBM) is a generative stochastic neural network that can be applied to collaborative filtering technique used by recommendation systems.  ...  Our tests show that the distributed training approach of the RBM model has a good scaling efficiency.  ...  Compliance with Ethical Standards Conflicts of interest On behalf of all authors, the corresponding author states that there is no conflict of interest.  ... 
doi:10.1007/s42979-020-00170-7 fatcat:pumuyhu4pvgrlj67x5bg7t2ob4

Parallelized Training of Restricted Boltzmann Machines using Markov-Chain Monte Carlo Methods [article]

Pei Yang, Srinivas Varadharajan, Lucas A. Wilson, Don D. Smith II, John A Lockman III, Vineet Gundecha, Quy Ta
2019 arXiv   pre-print
Restricted Boltzmann Machine (RBM) is a generative stochastic neural network that can be applied to collaborative filtering technique used by recommendation systems.  ...  Our tests show that the distributed training approach of the RBM model has a good scaling efficiency.  ...  popular model for collaborative filtering in recommendation system.  ... 
arXiv:1910.05885v1 fatcat:7ns5uqhctjexna2dq6gta5hgxy

Sparse Online Learning for Collaborative Filtering

Fan Lin, Xiuze Zhou, Wenhua Zeng
2016 International Journal of Computers Communications & Control  
., First Order Sparse Collaborative Filtering (SOCFI) and Second Order Sparse Online Collaborative Filtering (SOCFII), to deal with the user-item ratings for online collaborative filtering.  ...  <p>With the rapid growth of Internet information, our individual processing capacity has become over-whelming. Thus, we really need recommender systems to provide us with items online in real time.  ...  Our approaches are suitable to large-scale dynamic collaborative filtering scenario.  ... 
doi:10.15837/ijccc.2016.2.2144 fatcat:pm6hbkm7yfhazlopl7t4abv2ne

A Stochastic Sub-gradient Method for Low Rank Matrix Completion of Collaborative Recommendation

Weihua Yuan
2017 International Journal of Performability Engineering  
define an adaptive singular value thresholding operator, and put forward a kind of matrix completion model applicable for user-item rating matrix of collaborative filtering.  ...  Empirical results confirm that our proposed model and algorithm outperform several state-of-the-art matrix completion algorithms and the application to collaborative filtering recommendation can effectively  ...  Collaborative filtering as a popular recommender technique mainly relies on the user-item rating matrix to make recommendations.  ... 
doi:10.23940/ijpe.17.05.p9.643656 fatcat:v4ivxsou6revvibr4b4t7l6jve

Implementing Recommender Systems using Machine Learning and Knowledge Discovery Tools

Mohammad Zahrawi, Ahmad Mohammad
2021 Knowledge-Based Engineering and Sciences  
This article discovers the different characteristics and features of many approaches used for recommendation systems in order to filter and prioritize the relevant information and work as a compass for  ...  its own algorithm with a prize of 1 million dollars to win.  ...  Because computation increased linearly with datasets contain millions of consumers and products, collaborative filtering algorithm with the complexity of (n) becomes too large.  ... 
doi:10.51526/kbes.2021.2.2.44-53 fatcat:ludyzq53d5gubl3xmkvj2zku64

Social Popularity based SVD++ Recommender System

Rajeev Kumar, B. K. Verma, Shyam Sunder Rastogi
2014 International Journal of Computer Applications  
, we are actually using social information for recommendations.  ...  In the past few years, the incredible growth of Web 2.0 web sites and applications constitute new challenges for Traditional recommender systems.  ...  The weakness of Collaborative filtering based approach for large, sparse databases motivated us to investigate alternative recommender system algorithms.  ... 
doi:10.5120/15279-4033 fatcat:jwfwzozk5nbahb27fddc76orm4

Recommender Systems in Light of Big Data

Khadija A. Almohsen, Huda Al-Jobori
2015 International Journal of Electrical and Computer Engineering (IJECE)  
One of the successful techniques of RSs is collaborative filtering (CF) which makes recommendations for users based on what other like-mind users had preferred.  ...  This implementation is intended to validate the applicability of, existing contributions to the field of, SVD-based RSs as well as validated the effectiveness of Hadoop and spark in developing large-scale  ...  Another research effort should be dedicated to experiment other Big Data tools and framework such as Apache Mahout and compare its performance with Apache Spark.  ... 
doi:10.11591/ijece.v5i6.pp1553-1563 fatcat:jez2dwtmibhinp6ohi4jomgf5u

A Modified Similarity Measure for Improving Accuracy of User-Based Collaborative Filtering

2018 Iraqi Journal of Science  
Collaborative filtering is one of the most knowledge discovery techniques used positively in recommendation system.  ...  Similarity measures are the core operations in collaborative filtering; however, there is a certain deviance through using traditional similarity measures, which decreases the recommendation accuracy.  ...  [6] , in this paper, a singularity-based model is presented to get accurate prediction results for collaborative filtering in recommender system.  ... 
doi:10.24996/ijs.2018.59.2b.15 fatcat:kv3oxd7db5b2vgz7rvhoq2cbfu

Collaborative Filtering CAPTCHAs [chapter]

Monica Chew, J. D. Tygar
2005 Lecture Notes in Computer Science  
We propose a class of CAPTCHAs based on collaborative filtering.  ...  We analyze the security requirements of collaborative filtering CAPTCHAs and find that although they are not ready to use now, collaborative filtering CAPTCHAs are worthy of further investigation.  ...  Using Singular Value Decomposition in Collaborative Filtering Singular Value Decomposition (SVD) is a numerical method for doing collaborative filtering that separates user ratings by different features  ... 
doi:10.1007/11427896_5 fatcat:5k2ilecap5fp7mrppozgic67fa

A Study of Recommender System Techniques

Reena Pagare, Anita Shinde
2012 International Journal of Computer Applications  
Collaborative filtering techniques play vital component in recommender systems as they generate high-quality recommendations by influencing the likings of society of similar users.  ...  Recommender systems provide an important response to the information overload problem as it presents users more practical and personalized information services.  ...  RECOMMENDATION STRATEGIES The methods used for recommendations can be content based, collaborative filtering and trust based.  ... 
doi:10.5120/7269-0078 fatcat:mjigr6katzestnjfiqra2e7pxu
« Previous Showing results 1 — 15 out of 12,095 results