Reduction of Data Sparsity in Collaborative Filtering based on Fuzzy Inference Rules
Journal: International Journal of Advanced Computer Research (IJACR) (Vol.3, No. 10)Publication Date: 2013-06-28
Authors : Atisha Sachan; Vineet Richhariya;
Page : 101-107
Keywords : Collaborative Filtering; Sparsity; Accuracy; F uzzy Inference Rule; MovieLens;
- Implementation of 64-Point Reconfigurable FFT Processor for ASIP Architecture
- A RTOS Based Reconfigurable Architecture for IWSN Stack with Arm Cortex and EM250RF Processor Support
- FPGA Implementation of Reconfigurable Processor for Image Processing Application
- Flexible UDec ASIP Processor with Multimode Turbo Decoder
- Efficient Implementation of Reconfigurable MIMO Decoder Architecture
Abstract
Collaborative filtering Recommender system plays a very demanding and significance role in this era of internet information and of course e commerce age. Collaborative filt ering predicts user preferences from past user behaviour or user - item relationships. Though it has many advantages it also has some limitations such as sparsity, scalability, accuracy, cold start problem etc. In this paper we proposed a method that helps in reducing sparsity to enhance recommendation accuracy. We d eveloped fuzzy inference rules which is easily to implement and also gives better result. A comparison experiment is also performing with two previo us methods, Traditional Collaborative Filtering (TCF) and Hybrid User Model Technique (HUMCF).
Other Latest Articles
- Energy Efficient Routing Protocol for Wireless Sensor Networks
- A survey of Performance Analysis in MIMO-OFDM Systems
- Video Object Tracking based on Automatic Background Segmentation and updating using RBF neural network
- Monitoring Greenhouse using Wireless Sensor Network
- Implementation of FFT by using MATLAB: SIMULINK on Xilinx Virtex-4 FPGAs: Performance of a Paired Transform Based FFT
Last modified: 2014-11-28 22:34:28