The increasing volume of data in modern business and science calls for more complex and sophisticated tools. Although advances in data mining technology have made extensive data collection much easier, it's still always evolving and there is a constant need for new techniques and tools that can help us transform this data into useful information and knowledge. Since the previous edition's publication, great advances have been made in the field of data mining. Not only does the third of edition of Data Mining: Concepts and Techniques continue the tradition of equipping you with an understanding and application of the theory and practice of discovering patterns hidden in large data sets, it also focuses on new, important topics in the field: data warehouses and data cube technology, mining stream, mining social networks, and mining spatial, multimedia and other complex data. Each chapter is a stand-alone guide to a critical topic, presenting proven algorithms and sound implementations ready to be used directly or with strategic modification against live data. This is the resource you need if you want to apply today's most powerful data mining techniques to meet real business challenges. * Presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects. * Addresses advanced topics such as mining object-relational databases, spatial databases, multimedia databases, time-series databases, text databases, the World Wide Web, and applications in several fields. *Provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data

/pdf/data-mining-concepts-and-techniques-4dtvdfkvmi.pdf

Data Mining: Concepts and Techniques

Data Mining: Practical Machine Learning Tools and Techniques offers a thorough grounding in machine learning concepts as well as practical advice on applying machine learning tools and techniques in real-world data mining situations. This highly anticipated third edition of the most acclaimed work on data mining and machine learning will teach you everything you need to know about preparing inputs, interpreting outputs, evaluating results, and the algorithmic methods at the heart of successful data mining. Thorough updates reflect the technical changes and modernizations that have taken place in the field since the last edition, including new material on Data Transformations, Ensemble Learning, Massive Data Sets, Multi-instance Learning, plus a new version of the popular Weka machine learning software developed by the authors. Witten, Frank, and Hall include both tried-and-true techniques of today as well as methods at the leading edge of contemporary research. *Provides a thorough grounding in machine learning concepts as well as practical advice on applying the tools and techniques to your data mining projects *Offers concrete tips and techniques for performance improvement that work by transforming the input or output in machine learning methods *Includes downloadable Weka software toolkit, a collection of machine learning algorithms for data mining tasks-in an updated, interactive interface. Algorithms in toolkit cover: data pre-processing, classification, regression, clustering, association rules, visualization

Data Mining: Practical Machine Learning Tools and Techniques

A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented. It is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a randomly chosen non-diseased subject. Moreover, this probability of a correct ranking is the same quantity that is estimated by the already well-studied nonparametric Wilcoxon statistic. These two relationships are exploited to (a) provide rapid closed-form expressions for the approximate magnitude of the sampling variability, i.e., standard error that one uses to accompany the area under a smoothed ROC curve, (b) guide in determining the size of the sample required to provide a sufficiently reliable estimate of this area, and (c) determine how large sample sizes should be to ensure that one can statistically detect difference...

The meaning and use of the area under a receiver operating characteristic (ROC) curve.

An approach to the construction of classifiers from imbalanced datasets is described. A dataset is imbalanced if the classification categories are not approximately equally represented. Often real-world data sets are predominately composed of "normal" examples with only a small percentage of "abnormal" or "interesting" examples. It is also the case that the cost of misclassifying an abnormal (interesting) example as a normal example is often much higher than the cost of the reverse error. Under-sampling of the majority (normal) class has been proposed as a good means of increasing the sensitivity of a classifier to the minority class. This paper shows that a combination of our method of oversampling the minority (abnormal)cla ss and under-sampling the majority (normal) class can achieve better classifier performance (in ROC space)tha n only under-sampling the majority class. This paper also shows that a combination of our method of over-sampling the minority class and under-sampling the majority class can achieve better classifier performance (in ROC space)t han varying the loss ratios in Ripper or class priors in Naive Bayes. Our method of over-sampling the minority class involves creating synthetic minority class examples. Experiments are performed using C4.5, Ripper and a Naive Bayes classifier. The method is evaluated using the area under the Receiver Operating Characteristic curve (AUC)and the ROC convex hull strategy.

/pdf/smote-synthetic-minority-over-sampling-technique-5ap1gi5ups.pdf

SMOTE: synthetic minority over-sampling technique

https://ccrma.stanford.edu/workshops/mir2009/references/ROCintro.pdf

An introduction to ROC analysis

Book on statistical decision theory and sensory processes in signal detection theory and psychophysics

Signal detection theory and psychophysics

Diagnostic systems of several kinds are used to distinguish between two classes of events, essentially "signals" and "noise". For them, analysis in terms of the "relative operating characteristic" of signal detection theory provides a precise and valid measure of diagnostic accuracy. It is the only measure available that is uninfluenced by decision biases and prior probabilities, and it places the performances of diverse systems on a common, easily interpreted scale. Representative values of this measure are reported here for systems in medical imaging, materials testing, weather forecasting, information retrieval, polygraph lie detection, and aptitude testing. Though the measure itself is sound, the values obtained from tests of diagnostic systems often require qualification because the test data on which they are based are of unsure quality. A common set of problems in testing is faced in all fields. How well these problems are handled, or can be handled in a given field, determines the degree of confidence that can be placed in a measured value of accuracy. Some fields fare much better than others.

https://science.sciencemag.org/content/sci/240/4857/1285.full.pdf

Measuring the accuracy of diagnostic systems

About 5 years ago, the theory of statistical decision was translated into a theory of signal detection. Although the translation was motivated by problems in radar, the detection theory that resulted is a general theory for, like the decision theory, it specifies an ideal process. The generality of the theory suggested to us that it might also be relevant to the detection of signals by human observers. Beyond this, we were struck by several analogies between this description of ideal behavior and various aspects of the perceptual process. The detection theory seemed to provide a framework for a realistic description of the behavior of the human observer in a variety of perceptual tasks. 1 This paper is based upon Technical Report No. 40, issued by the Electronic Defense Group of the University of Michigan in 1955. The research was conducted in the Vision Research Laboratory of the University of Michigan with support from the United States Army Signal Corps and the Naval Bureau of Ships. Our thanks are due H. R. Blackwell and W. M. Kincaid for their assistance in the research, and D. H. Howes for suggestions concerning the presentation of this material. This paper was prepared in the Research Laboratory of Electronics, Massachusetts Institute of Technology, with support from the Signal Corps, Air Force (Operational Applications Laboratory and Office of Scientific Research), and Office of Naval Research. This is Technical Report No. ESD-TR-61-20. 2 For a formal treatment of statistical decision theory, see Wald (1950) ; for a brief and highly readable survey of the essentials, see Bross (1953). Parallel accounts of the detection theory may be found in Peterson, Birdsall, and Fox (1954) and in Van Meter and Middleton (1954). The particular feature of the theory that was of greatest interest to us was the promise that it held of solving an old problem in the field of psychophysics. This is the problem of controlling or specifying the criterion that the observer uses in making a perceptual judgment. The classical methods of psychophysics make effective provision for only a single free parameter, one that is associated with the sensitivity of the observer. They contain no analytical procedure for specifying independently the observer's criterion. These two aspects of performance are confounded, for example, in an experiment in which the dependent variable is the intensity of the stimulus that is required for a threshold response. The present theory provides a quantitative measure of the criterion. There is left, as a result, a relatively pure measure of sensitivity. The theory, therefore, promised to be of value to the student of personal and social processes in perception as well as to the student of sensory functions. A second feature of the theory that attracted us is that it is a normative theory. We believed that having a standard with which to compare the behavior of the human observer would aid in the description and in the interpretation of experimental results, and would be fruitful in suggesting new experiments. This paper begins with a brief review of the theory of statistical decision and then presents a description of the elements of the theory of signal detection appropriate to human observers.

John A. Swets

Papers

Signal detection theory and psychophysics

Measuring the accuracy of diagnostic systems

Decision processes in perception.

Evaluation of diagnostic systems : methods from signal detection theory

A decision-making theory of visual detection.