Module Descriptor School of Computer Science and Statistics

4 lectures and 1 lab per week.

To understand the theory and be able to apply the following techniques to  a set of data

• Classification and Regression Trees
• Ensemble methods

            Bagging

            Boosting

           Random forests

           RuleFit Procedute

• Evaluation of models

The aim of the course is to introduce the students to a set of techniques including classification and regression trees, and ensemble methods. Methods to evaluate models will also be discussed.

• Overview of Field

• Handling data

• Missing data

• Detailed discussion of Classification and Regression trees

• General Overview of Ensemble methods

• Detailed Discussion of Bagging

                                       Boosting

                                       Random Forests

                                       RuleFit Procedure

• Detailed discussion of Model evaluation

• Handling unbalanced datasets.

• Other methods of growing trees

• Stacking

• Ayres, I.  Supercrunchers, How anything can be predicted, John Murray, 2007.
• Berry M. J, A., & Linoff, G.  Data Mining Techniques, John Wiley & Sons, 2011.
• Bishop, Christopher, Pattern Recognition and Machine Learning, Springer Science, 2006.
• Breiman, L., Friedman, J. H. Olshen, R. A. & Stone, C. J.  Classification and regression Trees, Chapman and Hall,1984
• Davenport, T.H. Harris, J.G. Competing on Analytics, The New Science of Winning, Harvard Business School Press, 2007.
• Chang, Winston R Graphics Cookbook, O’Reilly, Sebastopol, CA, 2013
  
• Efron, Bradley & Hastie ,Trevor Computer Age Statistical Inference Algorithms, evidence and Data Science, Cambridge University Press, 2016 (available online).
• Hand, D., Mannila, H. & Smyth P. Principles of Data Mining, MIT Press, 2001.
• Hastie Trevor, Tibshirani, R., Friedman, J.  The Elements of Statistical Learning, 2^nd Edition, Springer Series, 2009
• James Gareth, Witten Daniela, Hastie Trevor, Tibshirani Robert, An Introduction to Statistical Learning, Springer Series, 2013
• Japkowicz, N & Shah Mohak Evaluating learning Algorithms, Cambridge University Press 2011.
• Kuhn, Max & Johnson, K. Applied Predictive Modeling, Springer, 2013.
• Ripley, B. D.  Pattern recognition and Neural Networks, Cambridge University  
• Seni, G. and Elder J. Ensemble methods in Data Mining, Morgan & Claypool, 2010
• Tan, Pang-Ning Steinbach, M. Kumar, V.  Introduction to Data Mining, Pearson, 2006
• Torgo, Luis Data Mining with R: Learning with Case Studies, Chapman and Hall, 2011
• Tuffery Stephane,  Data Mining and Statistics for Decision Making, John Wiley & Sons, 2011
• Unwin, A.  Graphical Data Analysis with R,CRC press, 2015
• Webb, Andrew, Copsey, K Statistical Pattern Recognition 3rd Edition, Wiley, 2011
• Zhou Zhi-Hua Ensemble Methods Foundation and Algorithms, Chapman and Hall, 2012

A course on Multivariate Analysis covering principal components multiple regression, clustering techniques and logistic regression.  A good working knowledge of R is also required.    

Students will be required to carry out a project worth 40% of the total marks with an exam in the n accounting for the remaining 60%.

Assessment in the Supplemental session will be based on 100% exam.