Skip to content
Introduction
- Linear classifiers
- Geometric interpretation of the data points
- Classification formalized
- Logistic regression
- Support vector machines
- Maximum margin hyperplane
- Lagrangian methods for optimization
- Primal problem
- Dual problem
- Application to maximum margin hyperplane
- Kernels and kernel trick
- Linear kernel
- Polynomial kernel
- Gaussian kernel (Radial basis function)
- Other kernels
- Soft margin classifiers
- Algorithm implementation
- Model building
- Data preprocessing
- Categorical variables
- Scaling and standardizing
- Grid search
- Missing values
- Feature selection
- Forward selection
- Backward selection
- F-score
- Genetic algorithm
- Model selection
- Hold-out cross validation
- k-fold cross validation
- Leave-one-out cross validation
- Model evaluation
- Support vector machines in Credit risk
- Application
- Peer to Peer Lending
- Data description
- Benchmark model: Logistic regression
- SVM with Linear kernel
- Optimal cost parameter search
- SVM with Gaussian kernel
- Model results
- Quantifying the edge
Conclusion
Bibliography
Appendix