Hands-On Data Science for Marketing by Yoon Hyup Hwang

Author:Yoon Hyup Hwang
Language: eng
Format: epub
Tags: COM062000 - COMPUTERS / Data Modeling and Design, COM004000 - COMPUTERS / Intelligence (AI) and Semantics, COM089000 - COMPUTERS / Data Visualization
Publisher: Packt Publishing
Published: 2019-03-29T07:02:11+00:00

User-based collaborative filtering and recommendations

In order to build a user-based collaborative filtering algorithm, we need to compute cosine similarities between users. Let's take a look at the following code:

# User-to-User Similarity Matrix

userToUserSimMatrix <- cosine(

as.matrix(

# excluding CustomerID column

t(customerItemMatrix[, 2:dim(customerItemMatrix)[2]])

)

)

colnames(userToUserSimMatrix) <- customerItemMatrix$CustomerID

As is noticeable from this code, using the cosine function from the coop library, you can compute and build a cosine similarity matrix. One thing to note in this code is the fact that we transpose the customerItemMatrix before computing cosine similarities. This is to compute user-to-user similarities. Without the transposition, the cosine function will be computing item-to-item similarities. Lastly, we are renaming the columns with customer IDs in the last line of this code.

The result looks as follows:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.