Summary

Content-based for recommendation tasks. Needs additional data about items however is independent of other users.

License

CC-BY-SA 3.0

Tags

content-based recommender system

Feature Processing

No processing is required, however method needs expert's data about items.

Parameters

Operating System

independent

Code

% Content based calssification algorithm % argmax_i Y_i'PP % where Y_i is matrix of ratings of all elements of Y equal to i and 0 % elsewhere

% Output % X - matrix to be estimated % Input % y - sampled entries % M - masking operator, applied to vectorized form of X % sizeX - size of matrix to be reconstructed % p - lp norm (default 1) % prop - properties of items

% Copyright (c) Lukasz Kidzinski 2011

Y = reshape(M(y,2),sizeX);

L = zeros(sizeX);
X = zeros(sizeX);
Z = Y';
for i=1:5
    pref = (Z.*(Z == i)) * prop;
    LIKE = pref * prop';
    LIKE = LIKE';
    X(LIKE > L) = i;
    L(LIKE > L) = LIKE(LIKE > L);
end

X(not (X > 1)) = mean(y);
X(X>5) = 5;

end

Software Packages

matlab/octave

Description

(No information yet)

URLs

http://students.mimuw.edu.pl/~lk234151/works/mgr-math.pdf

Publications

revision 1

by kidzik on 2011-09-13 20:07

revision 2

by kidzik on 2011-09-13 20:07

No one has posted any comments yet. Perhaps you would like to be the first?

Leave a comment

This item was downloaded 0 times and viewed 5588 times.