Description
- Introduction and business scenario
- CRISP-DM
- User interface
- Creating and managing repositories
- Loading data and summary statistics
- Visualising data
- Data preparation, handling missing values, normalisation, etc
- k-Nearest Neighbour
- Naïve Bayes
- Linear Regression
- Tree based methods, including bagging, random forest and GBM
- Ensemble modelling
- Bias, Variance, Overfitting and Underfitting
- Split and cross validation
- Evaluation methods & performance criteria
- Optimisation and parameter tuning
- Scoring models
