Building a Recommendation System with R电子书

Building a Recommendation System with R

Table of Contents

Building a Recommendation System with R

Credits

About the Authors

About the Reviewer

www.PacktPub.com

Support files, eBooks, discount offers, and more

Why subscribe?

Free access for Packt account holders

Preface

What this book covers

What you need for this book

Who this book is for

Citation

Conventions

Reader feedback

Customer support

Downloading the example code

Downloading the color images of this book

Errata

Piracy

Questions

1. Getting Started with Recommender Systems

Understanding recommender systems

The structure of the book

Collaborative filtering recommender systems

Content-based recommender systems

Knowledge-based recommender systems

Hybrid systems

Evaluation techniques

A case study

The future scope

Summary

2. Data Mining Techniques Used in Recommender Systems

Solving a data analysis problem

Data preprocessing techniques

Similarity measures

Euclidian distance

Cosine distance

Pearson correlation

Dimensionality reduction

Principal component analysis

Data mining techniques

Cluster analysis

Explaining the k-means cluster algorithm

Support vector machine

Decision trees

Ensemble methods

Bagging

Random forests

Boosting

Evaluating data-mining algorithms

Summary

3. Recommender Systems

R package for recommendation – recommenderlab

Datasets

Jester5k, MSWeb, and MovieLense

The class for rating matrices

Computing the similarity matrix

Recommendation models

Data exploration

Exploring the nature of the data

Exploring the values of the rating

Exploring which movies have been viewed

Exploring the average ratings

Visualizing the matrix

Data preparation

Selecting the most relevant data

Exploring the most relevant data

Normalizing the data

Binarizing the data

Item-based collaborative filtering

Defining the training and test sets

Building the recommendation model

Exploring the recommender model

Applying the recommender model on the test set

User-based collaborative filtering

Building the recommendation model

Applying the recommender model on the test set

Collaborative filtering on binary data

Data preparation

Item-based collaborative filtering on binary data

User-based collaborative filtering on binary data

Conclusions about collaborative filtering

Limitations of collaborative filtering

Content-based filtering

Hybrid recommender systems

Knowledge-based recommender systems

Summary

4. Evaluating the Recommender Systems

Preparing the data to evaluate the models

Splitting the data

Bootstrapping data

Using k-fold to validate models

Evaluating recommender techniques

Evaluating the ratings

Evaluating the recommendations

Identifying the most suitable model

Comparing models

Identifying the most suitable model

Optimizing a numeric parameter

Summary

5. Case Study – Building Your Own Recommendation Engine

Preparing the data

Description of the data

Importing the data

Defining a rating matrix

Extracting item attributes

Building the model

Evaluating and optimizing the model

Building a function to evaluate the model

Optimizing the model parameters

Summary

A. References

Index