Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Introduction to Machine Learning with Gradient Boosting Models

Go to class Write review

Overview

This course aims to introduce you to building and understanding gradient boosting models through practical application in financial market predictions. It centers on using the Gradient Boosting Regressor to forecast price changes in Tesla stock, encompassing model training, hyperparameter tuning, and evaluation.

Syllabus

Unit 1: Basic Gradient Boosting Model Training

Enhance Model by Adding the 'Close' Feature
Debug and Fix the Gradient Boosting Model
Fill in Missing Pieces for Model Training
Complete Gradient Boosting Model Implementation
Gradient Boosting Model Training with Tesla Data

Unit 2: Evaluating Model with Cross-Validation

Changing the Number of Cross-Validation Folds
Evaluate Cross-Validation
Complete the Cross-Validation and Model Instantiation
Complete Cross-Validation Evaluation
Evaluating Gradient Boosting Model with Cross-Validation

Unit 3: Hyperparameter Tuning Using GridSearchCV

Adjusting Cross-Validation Folds in GridSearchCV
Hyperparameter Tuning Debugging with GridSearchCV
Hyperparameter Tuning and Model Visualization
GridSearchCV for Hyperparameter Tuning
Hyperparameter Tuning with GridSearchCV

Unit 4: Feature Importance in Gradient Boosting Models

Remove Volume Feature for Better Analysis
Feature Importance Calculation in Gradient Boosting Models
Calculate and Visualize Feature Importance in Gradient Boosting Model
Computing and Visualizing Feature Importance
Compute and Visualize Feature Importance in Gradient Boosting Model

Unit 5: Using Early Stopping to Prevent Overfitting in Gradient Boosting Models

Apply Early Stopping Parameters to Model
Incorporate Early Stopping and Visualization in Gradient Boosting
Implementing a Gradient Boosting Regressor with Early Stopping

Reviews

Start your review of Introduction to Machine Learning with Gradient Boosting Models