Data Visualization

 

• How to use cutting-edge software to crunch large data sets into powerful and informative visualisations.
• Transform, understand and simplify data, using it to move your organisation from
• ‘What is data?’ to knowing why, when and how to use it for competitive advantage.

 

Introduction to Predictive Analytics

 

• Simple linear regression
• Multiple linear regression, interpretation, and basic inference

 

Predictive Modelling

 

• How to use data mining and probability to forecast outcomes.
• Identifying features that are likely to influence future results and successes using historical data

Classification

 

• Predict future successes and solve problems before they occur.

 

Model Accounting and Multicollinearity

 

• Extra and partial sums of squares, R-squared
• Newfood and Quality Control cases
• Multicollinearity
• Quality control case
• Residual, QQ and influence plots

 

Diagnostics and Transformations

 

• Transformations, the multiplicative model, polynomials
• Business failure and purifier cases

Categorical Predictor Variables, Interactions and Logistic Regression

 

• Dummy variables
• Interactions
• Logistic regression

 

Model Evaluation, Selection and Regularization

 

• Confusion tables, ROC curves, AUC
• Penalized measures of fit
• Test sets and k-fold cross validation
• Variable subset selection
• Ridge regression and the lasso

Midterm and Smoothing

 

• In-class midterm, 80 minutes, covers chapters 3 and 4 (not 5 and 6)
• Bin smoothers, k-nearest neighbors
• Step functions, piecewise linear models and cubic splines

 

GAMS and Trees

 

• Generalized additive models
• CART

Bagging, Random Forests, Principal Components

 

• Bagging and random forests
• Stumps, shrubs, boosted trees as time permits
• Principal component analysis

 

Clustering and Recommendation Systems

 

• K-means and hierarchical clustering
• Distance metrics
• Overview of recommendation systems: popularity, user-based, item-based, SVD as time permits
• How to develop meaningful segmentations or clusters with similarities.
• Develop more targeted customer engagement strategies or identify similar products and build recommendation engines.