DATA SCIENCE WITH MATLAB. SUPERVISED LEARNING TECHNIQUES. ENSEMBLE METHODS: BOOSTING, BAGGING, AND RANDOM FOREST

Data science is an interdisciplinary field that employs methods, algorithms, processes, and systems to extract insights and conclusions from structured and unstructured data. It combines elements of statistics, computer science, mathematics, and analytical techniques to solve problems, make predictions, and generate value from data. Machine learning techniques play a key role within the data analysis phase of data science. This book covers supervised learning techniques—specifically predictive classification methods such as ensemble methods (including Boosting, Bagging, and Random Forest)—as well as decision trees and regression trees. It also utilizes the Classification Learner app to train data classification models using supervised learning techniques. This app allows for the interactive exploration of supervised learning using various classifiers, automatically training a selection of models and facilitating the choice of the best one. Model types include ensemble methods, decision trees, discriminant analysis, support vector machines, logistic regression, nearest neighbors, among others. A variety of exercises are presented to facilitate the understanding of these techniques.