By default, Kraken runs several different algorithms based on the Metric selected for predictions. We use algorithms contained in the open source Python library, scikit-learn. The parameters that are used are scikit-learn's default values for each algorithm.

# Binary Classification Models

- Random Forest
- Logistic Regression
- XGBoost
- Nearest Neighbors Classification
- Support Vector Classification
- Gausian Naive Bayes

# Multi-Class Classification Models

- Random Forest
- Multinomial Logistic Regression
- Nearest Neighbors Classification
- Support Vector Classification
- Gausian Naive Bayes

# Regression Models

- Linear Regression
- Random Forest Regression
- XGB Regressor
- Nearest Neighbors Regressor
- Support Vector Regression
- Stochastic Gradient Descent Regression