TYPICALITY-BASED COLLABORATIVE FILTERING
RECOMMENDATION
ABSTRACT:
Collaborative
filtering (CF) is an important and popular technology for recommender systems.
However, current CF methods suffer from such problems as data sparsity,
recommendation inaccuracy and big-error in predictions. In this paper, we
borrow ideas of object typicality from cognitive psychology and propose a novel
typicality-based collaborative filtering recommendation method named TyCo.
A distinct feature of typicality-based CF is that it finds ‘neighbours’ of
users based on user typicality degrees in user groups (instead of the co-rated
items of users, or common users of items, as in traditional CF). To the best of
our knowledge, there has been no prior work on investigating CF recommendation
by combining object typicality. TyCo outperforms many CF recommendation methods
on recommendation accuracy (in terms of MAE) with an improvement of at least
6.35% in Movielens Data set, especially with sparse training data (9.89%
improvement on MAE) and has lower time cost than other CF methods. Further, it
can obtain more accurate predictions with less number of big-error predictions.
EXISTING SYSTEM:
The
basic idea of user-based CF approach is to find out a set of users who have
similar favour patterns to a given user (i.e., ‘neighbours’ of the user) and
recommend to the user those items that other users in the same set like, while the
item-based CF approach aims to provide a user with the recommendation on an
item based on the other items with high correlations (i.e., ‘neighbours’ of the
item). In all collaborative filtering methods, it is a significant step to find
users’ (or items’) neighbours, that is, a set of similar users (or items).
Currently, almost all CF methods measure users’ similarity (or items’
similarity) based on co-rated items of users (or common users of items).
Although these recommendation methods are widely used in E-Commerce, a number
of inadequacies have been identified.
DISADVANTAGES OF
EXISTING SYSTEM:
v It
is difficult to find out correlations between users and items.
v Major
issue that limits the quality of CF recommendations.
v Some
predictions provided by current systems may be very different from the actual
preferences or ratings given by users. These inaccurate predictions, especially
the bigerror.
PROPOSED
SYSTEM:
in
this paper, we borrow the idea of object typicality from cognitive psychology
and propose a typicalitybased CF recommendation approach named TyCo. The
mechanism of typicality-based CF recommendation is as follows. First, we
cluster all items into several item groups. For example, we can cluster all
movies into ‘war movies,’ ‘romance movies,’ and so on. Second, we form a user
group corresponding to each item group (i.e., a set of users who like items of
a particular item group), with all users having different typicality degrees in
each of the user groups. Third, we build a user-typicality matrix and measure
users’ similarities based on users’ typicality degrees in all user groups so as
to select a set of ‘neighbours’ of each user.
Then
we predict the unknown rating of a user on an item based on the ratings of the
‘neighbours’ of at user on the item.
ADVANTAGES OF PROPOSED
SYSTEM:
v
It generally improves the accuracy of
predictions when compared with previous recommendation methods.
v
It works well even with sparse training
data sets, especially in data sets with sparse ratings for each item.
v
It can reduce the number of big-error
predictions.
SYSTEM CONFIGURATION:-
HARDWARE REQUIREMENTS:-
Processor - Pentium –IV
Speed - 1.1 Ghz
RAM - 512 MB(min)
Hard Disk - 40 GB
Key Board - Standard Windows Keyboard
Mouse - Two or Three Button Mouse
Monitor - LCD/LED
SOFTWARE
REQUIREMENTS:
Operating
system : Windows XP.
Coding
Language : .Net
Data
Base : SQL Server 2005
Tool : VISUAL STUDIO 2008.
REFERENCE:
Yi
Cai_, Ho-fung Leung†, Qing Li_, Huaqing Min_, Jie
Tang_ and Juanzi Li_, “Typicality-based
Collaborative Filtering Recommendation” IEEE TRANSACTIONS ON KNOWLEDGE AND
DATA ENGINEERING, VOL. 28, NO. 3, March 2014
No comments:
Post a Comment