Information Management Course

General Informations

Lecture topics and slides

• Lecture 01 (Oct 2nd '12): Introduction to Information Management and Data Mining (slides in LibreOffice and (slides in pdf format); motivation and examples; main issues in data mining.
• Lecture 02 (Oct 3rd '12): Know your data (slides in LibreOffice and slides in pdf format); data objects and attribute types, basic statistical descriptions of data, measuring data proximity.
• Lecture 03 (Oct 9th '12): Data preprocessing - part 1 - (slides in LibreOffice and slides in pdf format); the quality of data; data cleaning, integration and reduction.
• Lecture 04 (Oct 10th '12): Exercise session 01 - Introduction to R (list of topics ; dataset: Breast Cancer Wisconsin ).
• Lecture 05 (Oct 24th '12): Data preprocessing - part 2 -; (slides in LibreOffice and slides in pdf format); On Line Analytical Processing and Data Warehousing - part 1 - (slides in LibreOffice and slides in pdf format);
• Lecture 06 (Oct 25th '12): Principal Component Analysis (slides in LibreOffice and slides in pdf format); Exercise session 02: PCA in practice using R ( dataset for Lab experiments).
• Lecture 07 (Nov 6th '12): Data Warehousing - part 2 - and Data Cube technology (slides in LibreOffice and slides in pdf format); Introduction to the Feature Selection problem (slides in LibreOffice and slides in pdf format).
• Lecture 08 (Nov 7th '12): Principal Component Analysis (slides in LibreOffice and slides in pdf format); Exercise session 03: understanding PCA results in R, components selection criteria ( forest fires dataset for Lab experiments).
• Lecture 09 (Nov 13th '12): Feature Selection Algorithms (slides in LibreOffice and slides in pdf format);
• Lecture 10 (Nov 14th '12): Excercise session 04 - Feature Selection Algorithms in R; implementation of evaluation measures and Las Vegas Filter Algorithms ( elections dataset and audiology dataset ).
• Lecture 11 (Nov 20th '12): Mining frequent patterns, ideas and basic algorithms (slides in LibreOffice and slides in pdf format);
• Lecture 12 (Nov 21st '12): Excercise session 05 - Feature Selection Algorithms in R; implementation of Sequential (Forward and Backward), Floating Sequential and FOCUS Algorithms; empirical and experimental analysis of FSAs (slides in LibreOffice and slides in pdf format).
• Lecture 13 (Nov 27th '12): Mining frequent patterns: FPGrowth and Vertical Data Format Algorithms; Pattern evaluation measures. (slides in LibreOffice and slides in pdf format).
• Lecture 14 (Nov 28th '12): Excercise session 06 - FSA algorithms in R; implementation of evaluation measures and Las Vegas Filter Algorithms Mining frequent patterns ( elections dataset and corresponding attribute names, and audiology dataset ).
• Lecture 15 (Dec 4th '12): Classification: basic concepts and ideas; classifying using decision tree induction models and algorithms. (slides in LibreOffice and slides in pdf format).
• Lecture 16 (Dec 5th '12): Excercise session 07 - Decision tree induction: information gain indices; inducing decision trees in R ( computing Information measures).
• Lecture 17 (Dec 11th '12): Bayesian classification; Bayesian Belief Networks. (slides in LibreOffice and slides in pdf format).
• Lecture 18 (Dec 12th '12): Support Vector Machines; classification models evaluation and metrics; Building Bayesian models and SVMs in R. (slides in LibreOffice and slides in pdf format); portion of R code on how to use a SVM library implementation. .
• Lecture 19 (Dec 18th '12): Clustering: partitioning, hierarchical and density-based methods. (slides in LibreOffice and slides in pdf format).
• Lecture 20 (Dec 19th '12): Evaluation of clustering methods; implementing k-means in R. (slides in LibreOffice and slides in pdf format). A k means implementation in R .

Pointers to related material

• The reference textbook for the course is "Data Mining: concepts and techniques" by J. Han, M. Kamber and J. Pei (3rd edition).
• Lectures 6 and 8 are adapted from "Data Mining methods and models" by D.T. Larose .
• Lectures 7, 9, 10 and 12 are adapted from L.C. Molina, L. Belanche, A. Nebot "Feature Selection Algorithms: a survey and experimental evaluation", proc. of IEEE ICDM 2002 and L. Belanche, F. Gonzales "Review and Evaluation of Feature Selection Algorithms in Synthetic Problems", arxiv 2011.
• Lecture 18 is partially adapted from C. Vercellis "Business Intelligence: Data Mining and Optimization for Decision Making", Wiley and sons, 2011 .
• The former editions of the Information Management course were held by prof. A. Tettamanzi: you can find syllabus and slides at the corresponding website.