METHOD FOR COLLABORATIVELY FILTERING INFORMATION IN USE OF PERSONALIZED REGRESSION WITH CONTEXT INFORMATION TO PREDICT PREFERENCE GIVEN BY USER OF ITEM TO THE ITEM AND COMPUTING APPARATUS USING THE SAME

摘要

The present invention relates to a method of purifying information in order to predict a user's preference given to the item, and a computing device using the method. According to the present invention, the computing device obtains the data ruic of the preference that the individual user u has given to the individual item i under the context parameter c, To minimize And the average Estimator of Where U denotes a set of individual users, I denotes a set of individual items, C denotes a set of individual context variables, and r _uic denotes a set of individual users u (U, i, c) when the individual user u gives preference under the context variable c to the individual item i is defined as an _element of R _uic , which is a random variable indicating the preference given under the variable c. , And c denotes a set having Lt; ego, Lt; ego, And, λ _U is to refer to a tuning parameter (tuning parameter) relating to U and, λ _I refers to the tuning parameters of the I, λ _k is refers to the tuning parameters of the context variable c _k, and then, the computing estimate of the device, the average μ _uic The residual And using the residual to calculate a covariance matrix for the preference of the user u Is calculated, Is dispensed the variation of each user-specific preferences related to the preferences of the user u, and then, the conditional expectation of R _uic as the estimated preference data for a specific user u under the context of a variable c for the individual items at least one item of i, each of the Value .