Logistic Regression
A statistical model that estimates the probability of a binary outcome using a sigmoid function. Fast to train and highly interpretable, it works best when the relationship between features and the target is approximately linear — making it a strong baseline for classification tasks.
|
Support Vector Classification
Finds the optimal hyperplane that maximally separates classes in feature space. With the kernel trick, it can handle non-linear boundaries effectively. Particularly powerful on high-dimensional data and small-to-medium datasets where margin maximization gives a performance edge.
|
XGBoost
An optimized gradient boosting framework that builds an ensemble of decision trees sequentially, each correcting the errors of the last. Known for its speed, regularization capabilities, and consistently strong performance on structured/tabular data — a go-to for competitive machine learning.
|
Multi-Layer Perceptron
A feedforward neural network composed of multiple layers of interconnected neurons with non-linear activation functions. Capable of learning complex, hierarchical patterns in data, it bridges classical ML and deep learning — well-suited for tasks where feature interactions are rich and datasets are sufficiently large.
|