Evaluating the Performance of a Biclustering Algorithm Applied to Collaborative Filtering - A Comparative Analysis

Author(s):  
Pablo A. D. de Castro ◽  
Fabricio O. de Franca ◽  
Hamilton M. Ferreira ◽  
Fernando J. Von Zuben
2021 ◽  
Author(s):  
Markos F. B. G. Oliveira ◽  
Myriam Delgado ◽  
Ricardo Lüders

Collaborative Filtering (CF) can be understood as the process of predicting the preferences of users and deriving useful patterns by studying their activities. In the survey context, it can be used to predict answers to questions as combinations of other available answers. In this paper, we aim to test five CF-based algorithms (item-item, iterative matrix factorization, neural collaborative filtering, logistic matrix factorization, and an ensemble of them) to estimate scores in four survey applications (checkpoints) composed of 700,000 employee's ratings. These data have been collected from 2019 to 2020 by a large Brazilian tech company with more than 10,000 employees. The results show that collaborative filtering approaches provide relevant alternatives to score questions of surveys. They provided good quality estimates. This result can be further explored to eventually reduce the size of questionnaires, avoiding burden phenomena faced by respondents when dealing with large surveys.


2015 ◽  
Vol 713-715 ◽  
pp. 1615-1621
Author(s):  
Xiu Juan Li ◽  
He Biao Yang

Coupled with exponential expansion of the data, efficient computing of existing recommendation algorithm has become an important issue, and the traditional collaborative filtering recommendation algorithm also exist the problem of sparsity. Based on the detailed analysis, the article introduce Hadoop platform into improved collaborative filtering recommendation algorithm, the improved collaborative filtering recommendation algorithm solve the problem of data sparsity, MapReduce parallel computing of recommendation also solve the promble of computational efficiency. In the experiments, the comparative analysis between Hadoop platform implementation and the previous implementation draws the conclusion that the Hadoop platform improves collaborative filtering recommendation algorithm computation efficiently under conditions of large data sets.


2019 ◽  
Vol 16 (9) ◽  
pp. 3892-3896
Author(s):  
Bhavana ◽  
Neeraj Raheja

Recommendation systems are intelligent system which provides suggestion according to user adaptability. Recommender systems i.e., collaborative filtering and content filtering works on the basis of user profiles, extensive history of user preferences and item descriptions. This paper proposes an improved recommendation system based on clustering approach. The comparative analysis shows that the proposed system provides better results in terms of RMSE as compared to other already existing methods.


Sign in / Sign up

Export Citation Format

Share Document