Business-Analytics

Course homepage for "Business Analytics" @Korea University

Notice

• Course syllabus: download
• Tutorial resources (2015)
• Tutorial resources (2016)

Schedule

Topic 1: Dimensionality Reduction

• Dimensionality Reduction: Overview
• Supervised Methods: Forward selection, Backward elimination, Stepwise selection, Genetic algorithm
• Unsupervised Method (Linear embedding): Principal component analysis (PCA), Multi-dimensional scaling (MDS)
• Unsupervised Method (Nonlinear embedding): ISOMAP, LLE, t-SNE
• Tutorial 1: Supervised Method (장명준)
  • Tutorial Video
  • Evaluation (Due: 10/18)
• Tutorial 2: Unsupervised Method (Linear embedding) (정재윤, due: 10/18)
  • Tutorial Video
  • Evaluation (Due: 11/01)
• Tutorial 3: Unsupervised Method (Nonlinear embedding) (서승완, due: 10/25)
  • Tutorial Video
  • Evaluation (Due: 11/08)

Topic 2: Kernel-based Learning

• Theoretical foundation
• Support Vector Machine (SVM)
• Support Vector Regression (SVR)
• Kernel Fisher Discriminant Analysis (KFDA)
• Kernel Principal Component Analysis (KPCA)
• Tutorial 4: Support Vector Machine (SVM) (성유연, due: 11/01)
  • Tutorial Video
  • Evaluation (Due: 11/15)
• Tutorial 5: Support Vector Regression (SVR) (이민정, due: 11/08)
  • Tutorial Video
  • Evaluation (Due: 11/29)
• Tutorial 6: Kernel Fisher Discriminant Analysis (KFDA) (조윤상, due: 11/08)
  • Tutorial Video
  • Evaluation (Due: 11/29)
• Tutorial 7: Kernel Principal Component Analysis (KPCA) (채선율, due: 11/08)
  • Tutorial Video
  • Evaluation (Due: 11/29)

Topic 3: Novelty Detection

• Novelty detection: Overview
• Density-based novelty detection
• Distance/Reconstruction-based novelty detection
• Model-based novelty detection
• Applications
• Tutorial 8: Density-based novelty detection (전창동, 오주혁, due: 11/22)
  • Tutorial Video
  • Evaluation (Due: 12/06)
• Tutorial 9: Distance/Reconstruction-based novelty detection (옥명훈, due: 11/29)
  • Tutorial Video
  • Evaluation (Due: 12/13)
• Tutorial 10: Model-based novelty detection (송서하, 최현율, due: 11/29)
  • Tutorial Video
  • Evaluation (Due: 12/13)

Topic 4: Ensemble Learning

• Motivation and theoretical backgrounds
• Bagging
• Boosting: AdaBoost, Gradient Boosting
• Tree-based Ensemble: Random Forests, Decision Jungle
• Tutorial 11: Bagging (이주한, due: 12/6)
  • Tutorial Video
  • Evaluation (due: 12/27)
• Tutorial 12: AdaBoost, Gradient Boosting (김명소, 송은영, due: 12/13)
  • Tutorial Video
  • Evaluation (Due: 12/27)
• Tutorial 13: Random Forests, Decision Jungle (임희찬, 권상현, due: 12/13)
  • Tutorial Video
  • Evaluation (Due: 12/27)

Topic 5: Semi-supervised Learning

• Overview
• Self-training
• Generative models
• Semi-supervised SVM
• Graph-based SSL
• Multi-view algorithm (Co-training)
• Tutorial 14: Self-training (김우일, due: 12/20)
  • Tutorial Video
  • Evaluation (Due: 12/27)
• Tutorial 15: Generative models (강성호, due: 12/20)
  • Tutorial Video
  • Evaluation (Due: 12/27)
• Tutorial 16: Graph-based SSL (안건이, due: 12/27)
  • Ipython notebook, Video
• Tutorial 17: Multi-view algorithm (Co-training) (이준헌, due: 12/27)
  • Tutorial Video
  • Evaluation (Due: 12/31)