Data mining for the masses / Matthew North

Data mining for the masses /, Data

Section 1. Data mining basics -- 1. Introduction to data mining and CRISP-DM -- 2. Organizational understanding and data understanding -- 3. Data preparation -- Section 2. Data mining models and methods -- 4. Correlational methods -- 5. Association rules -- 6. k-means clustering -- 7. Discriminant analysis, k-Nearest neighbors and Naive Bayes -- 8. Linear regression -- 9. Logistic regression -- 10. Decision trees -- 11. Neural networks -- 12. Text mining -- Section 3. Special considerations in data mining -- 13. Evaluation and deployment -- 14.Data mining ethics.

We live in a world that generates tremendous amounts of data—more than ever before. In business, and in our personal lives, we use smartphones and tablets, web sites and watches; with dozens of apps and interfaces to shop, learn, entertain and inform. Businesses increasingly use technology to interact with consumers to provide marketing, customer service, product information and more. All of this technological activity generates data—data that can be useful in many ways. Data mining can help to identify interesting patterns and messages that exist, often hidden beneath the surface. In this modern age of information systems, it is easier than ever before to extract meaning from data. From classification to prediction, data mining can help. In Data Mining for the Masses, Second Edition, professor Matt North—a former risk analyst and software engineer at eBay—uses simple examples and clear explanations with free, powerful software tools to teach you the basics of data mining. In this Second Edition, implementations of these examples are offered in both an updated version of the RapidMiner software, and in the popular R Statistical Package.