Introduction to Data Mining

Objectives: The main purpose of the course is to analyze and construct knowledge from data. The objective of the course is to enhance the students' understanding and awareness of the concepts of the data mining basics, algorithms, techniques, and applications in different cross disciplinary domains. The course will build on the programming, problem-solving and statistics skills, developed in previous subjects studied by the student, to achieve an understanding of the implementation of techniques for scenarios requiring classification and prediction.

Contents: The knowledge discovery process in databases, data mining process, types of attributes, role of data mining from machine learning perspective, supervised and unsupervised learning, Pre-processing: data cleansing and data preparation, classification and prediction: Naïve Bayes, decision tree, K-Nearest Neighbors, mining association rules, rules interestingness measures, Apriori algorithm, Clustering: K-means, K-median, Divisive, Hierarchical, Density based. Case studies of data mining application in the domains of Management e.g. Churn Detection and Surveys Analysis, Financial e.g. fraud detection, Information Security e.g. hacking patterns, Science e.g. climate change prediction, Medicine e.g. patient disease diagnosis, Psychology e.g. behavior analysis.