Missing Value Prediction Using Co-clustering and RBF for Collaborative Filtering

2015 ◽  
Author(s):  
Youchun Ji ◽  
Wenxing Hong ◽  
Jianwei Qi
Keyword(s):  
Collaborative Filtering ◽  
Missing Value ◽  
Value Prediction ◽  
Missing Value Prediction

Enhance the Quality of Collaborative Filtering using Tagging

2020 ◽  
Vol 13 ◽  
Author(s):  
Latha Banda ◽  
Karan Singh
Keyword(s):  
Genetic Algorithm ◽  
Collaborative Filtering ◽  
Cold Start ◽  
Collaborative Tagging ◽  
Rating Data ◽  
Missing Value ◽  
Value Prediction ◽  
Sparsity Problem ◽  
Missing Value Prediction ◽  
Weight Model

Background: Due to enormous data in web sites, recommending users for every item is impossible. For this problem Recommender Systems (RS) are introduced. RS is categorized into content-based (CB), collaborative Filtering (CF) and Hybrid RS. Based on these techniques recommendations are done to user. In this, CF is the recent technique used in RS in which tagging features also provided. Objective: Three main issues occur in RS are scalability problem which occurs when there is a huge data, sparsity problem occurs when rating data is missing and cols start user or item problem occurs when new user or new item enters in the system. To avoid these issues here we have proposed Tag and Time weight model with GA in Collaborative Tagging. Method: Here we have proposed a method Collaborative Tagging (CT) with Tag and Time weight model with real value genetic algorithm which enhances the recommendation quality by removing the issues of sparsity and cold start user problems with the help of missing value prediction. Here in this the sparsity problem can be removed using missing value prediction and cold start problems are removed using tag and time weight model using GA. Results: Here we have compared the results of Collaborative Filtering with cosine similarity (CF-CS), Collaborative Filtering with Diffusion Similarity (CF-DS), Tag and Time weight model with Diffusion similarity (TAW-TIW-DS) and Tag and Time weight model using Diffusion similarity and Genetic algorithm (TAW-TIW-DS-GA). Conclusion: Here we have compare the proposed approach with the baseline approaches and the metrics are used MAE, prediction percentage, Hit-rate and Hit-rank. Based on these metrics for every split TAW-TIW-DS-GA shown best results as compared to existing approach.

Sign in / Sign up

Export Citation Format

Share Document