Working with imbalanced data in 2024 | Train in Data

This site uses cookies

Cookies are important for this site to function properly, to guarantee your safety, and to provide you with the best experience. By continuing to browse, you agree to the use of these cookies.
Learn More.

Autoplay
Autocomplete

Previous Lesson Complete and Continue

Machine Learning with Imbalanced Data

Welcome

Introduction (5:01)
Course Curriculum Overview (4:48)
Working with imbalanced data in 2024 (14:37)
Additional resources

Course material

Course Material (1:37)
Code | Jupyter notebooks
Presentations covered in the course
Download Datasets
Python package Imbalanced-learn
How did you hear about us?

Machine Learning with Imbalanced Data: Overview

Introduction to imbalanced data (5:24)
Nature of the imbalanced class (4:56)
Approaches to work with imbalanced datasets (3:59)
Reading Resources
Refer a friend program
Quiz

Evaluation Metrics

Introduction to Performance Metrics (3:22)
Accuracy (4:21)
Accuracy - Demo (5:39)
Precision, Recall and F-measure (13:32)
Install Yellowbrick
Precision, Recall and F-measure - Demo (10:04)
Confusion tables, FPR and FNR (6:03)
Confusion tables, FPR and FNR - Demo (7:32)
Balanced Accuracy (3:49)
Balanced accuracy - Demo (2:43)
Geometric Mean, Dominance, Index of Imbalanced Accuracy (4:29)
Geometric Mean, Dominance, Index of Imbalanced Accuracy - Demo (9:28)
ROC-AUC (7:26)
ROC-AUC - Demo (4:46)
Precision-Recall Curve (11:19)
Precision-Recall Curve - Demo (3:53)
Additional reading resources
Probability (4:32)
Tuning the probability threshold with sklearn (8:24)
Bringing it all together - credit risk (13:14)
Quiz - binary classification
Metrics for Mutliclass (11:04)
Metrics for Multiclass - Demo (8:55)
PR and ROC Curves for Multiclass (5:16)
PR Curves in Multiclass - Demo (8:40)
ROC Curve in Multiclass - Demo (7:13)
Quiz - multiclass classification
How are we doing? (0:26)

Cost Sensitive Learning

Cost-sensitive Learning (7:27)
Types of Cost (10:55)
Obtaining the Cost (4:28)
Cost Sensitive Approaches (1:52)
Misclassification Cost in Logistic Regression (3:35)
Misclassification Cost in Decision Trees (3:50)
Cost Sensitive Learning with Scikit-learn (7:13)
Find Optimal Cost with hyperparameter tuning (3:33)
Cost sensitive learning - credit risk (6:44)
Cost sensitive learning in ensemble methods
CSL: before or after feature engineering?
Cost-sensitive pipelines (2:38)
Quiz - cost sensitive learning
Bayes Conditional Risk (13:44)
MetaCost (8:03)
MetaCost - Demo (3:40)
Optional: MetaCost Base Code (6:39)
Wrapping up (2:57)
How are we doing? (0:24)
Additional Reading Resources

Udersampling

Under-Sampling Methods - Introduction (5:21)
Random Under-Sampling - Intro (4:23)
Random Under-Sampling - Demo (10:11)
Condensed Nearest Neighbours - Intro (8:03)
Condensed Nearest Neighbours - Demo (7:25)
Tomek Links - Intro (4:43)
Tomek Links - Demo (3:05)
One Sided Selection - Intro (4:38)
One Sided Selection - Demo (3:00)
Edited Nearest Neighbours - Intro (5:01)
Edited Nearest Neighbours - Demo (4:02)
Repeated Edited Nearest Neighbours - Intro (4:39)
Repeated Edited Nearest Neighbours - Demo (3:00)
All KNN - Intro (6:16)
All KNN - Demo (5:50)
Neighbourhood Cleaning Rule - Intro (6:14)
Neighbourhood Cleaning Rule - Demo (1:55)
NearMiss - Intro (3:47)
NearMiss - Demo (3:53)
Instance Hardness Threshold - Intro (9:20)
Instance Hardness Threshold - Demo (16:21)
Instance Hardness Threshold Multiclass Demo (7:44)
Undersampling Method Comparison (7:44)
Quiz - undersampling comparison
Setting up a classifier with under-sampling and cross-validation (10:54)
Quiz - comparison with cross-validation
Undersampling methods comparison with hyperparameter tuning
Wrapping up the section (5:18)
How are we doing? (0:24)
Summary Table
Added Treat: A Movie We Recommend 🍿

Oversampling

Over-Sampling Methods - Introduction (3:41)
Random Over-Sampling (5:00)
Random Over-Sampling - Demo (4:55)
ROS with smoothing - Intro (6:39)
ROS with smoothing - Demo (4:36)
SMOTE (9:26)
SMOTE - Demo (2:35)
SMOTE-NC (9:02)
SMOTE-NC - Demo (2:56)
SMOTE-N (19:25)
SMOTE-N Demo (7:20)
ADASYN (7:11)
ADASYN - Demo (3:17)
Borderline SMOTE (7:47)
Borderline SMOTE - Demo (3:13)
SVM SMOTE (16:40)
Resources on SVMs
SVM SMOTE - Demo (4:32)
K-Means SMOTE (13:01)
K-Means SMOTE - Demo (3:29)
Over-Sampling Method Comparison (5:50)
Quiz - oversampling methods comparison
Oversampling method comparison - take 2
Wrapping up the section (9:30)
SMOTE in 2024
How to Correctly Set Up a Classifier with Over-sampling (5:24)
Summary Table
Extra Treat: Our Reading Suggestion 📕

Over and Undersampling

Combining Over and Under-sampling (6:02)
SMOTE + ENN and SMOTE + Tomek Links - Demo (5:26)
Comparison of Over and Under-sampling Methods (5:54)
Combine over and under-sampling manually
Wrapping up (2:08)

Ensemble Methods

Ensemble methods with Imbalanced Data (4:33)
Foundations of Ensemble Learning (3:12)
Bagging (3:04)
Bagging with over- or undersampling (5:38)
Boosting (10:03)
Boosting with resampling (7:05)
Hybdrid Methods (4:48)
Ensemble Methods - Demo (9:59)
Comparison of ensemble methods
Wrapping up (5:31)
Additional Reading Resources
More Wisdom: Our Chosen Podcast Episode 🎧

Probability Calibration

Probability Calibration (6:41)
Probability Calibration Curves (5:56)
Probability Calibration Curves - Demo (9:37)
Brier Score (3:06)
Brier Score - Demo (7:07)
Under- and Over-sampling and Cost-sensitive learning on Probability Calibration (5:10)
Calibrating a Classifier (5:25)
Calibrating a Classifier - Demo (6:20)
Calibrating a Classfiier after SMOTE or Under-sampling (8:05)
Calibrating a Classifier with Cost-sensitive Learning (3:31)
Quiz
Additional reading resources

Wrapping-up

Wrapping-up (8:58)
Assignment

Next steps

Congratulations
Next steps

Working with imbalanced data in 2024

Complete and Continue

Discussion

0 comments