R and Data Mining Examples and Case Studies

About this book

R and Data Mining introduces using R for data mining. Data mining techniques are widely used in government agencies, banks, insurance, retail, telecom, medicine and research. Recently, there is an increasing tendency to do data mining with R, a free software environment for statistical computing and graphics. According to a poll by KDnuggets.com in early 2011, R is the 2nd popular tool for data mining work.

By introducing using R for data mining, R and Data Mining will have a broad audience from both academia and industry. It targets researchers in the field of data mining, postgraduate students who are interested in data mining, and data miners and analysts from industry. For example, many universities have courses on data mining, and the proposed book will be a useful reference for students learning data mining in those courses. There are also many training courses on data mining in industry, such as training by SAS and IBM on data mining.

R and Data Mining will be of interest to the course learners as well. It presents an introduction into using R for data mining applications, covering most popular data mining techniques. It provides code examples and data so that readers can easily learn the techniques. It features case studies in real-world applications to help readers apply the techniques in their work.

Contents

Introduction
        Introduction, Data mining
            R
            Datasets used in this book
    Data Loading and Exploration
        Data Import/Export
            Save/Load R Data
            Import from and Export to .CSV Files
            Import Data from SAS
            Import/Export via ODBC
        Data Exploration
            Have a Look at Data
            Explore Individual Variables
            Explore Multiple Variables
            More Exploration
            Save Charts as Files
    Data Mining Examples
        Decision Trees
            Building Decision Trees with Package party
            Building Decision Trees with Package rpart
            Random Forest
        Regression
            Linear Regression
            Logistic Regression
            Generalized Linear Regression
            Non-linear Regression
        Clustering
            K-means Clustering
            Hierarchical Clustering
            Density-based Clustering
        Outlier Detection
        Time Series Analysis
            Time Series Decomposition
            Time Series Forecast
        Association Rules
        Sequential Patterns
        Text Mining
        Social Network Analysis
    Case Studies
        Case Study I: Analysis and Forecasting of House Price Indices
            Reading Data from a CSV File
            Data Exploration
            Time Series Decomposition
            Time Series Forecasting
            Discussion
        Case Study II: Customer Response Prediction
        Case Study III: Risk Rating using Decision Tree with Limited Resources
        Customer Behaviour Prediction and Intervention
    Appendix
        Online Resources
        R Reference Card for Data Mining
Bibliography

Customer Reviews

Biography

Yanchang Zhao is a Senior Data Mining Analyst in Australia Government since 2009. Before joining public sector, he was an Australian Postdoctoral Fellow (Industry) in the Faculty of Engineering & Information Technology at University of Technology, Sydney, Australia. His research interests include clustering, association rules, time series, outlier detection and data mining applications and he has over forty papers published in journals and conference proceedings. He is a member of the IEEE and a member of the Institute of Analytics Professionals of Australia, and served as program committee member for more than thirty international conferences.