Weighted Shapley Values and Weighted Confidence Intervals for Multiple Machine Learning Models and Stacked Ensembles

MICCAI 2023: DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation

Content: Machine Learning, Logistic regression steps, Probability matrix, Confusion matrix, Accuracy score, Recall value, Data preprocessing, Label encoding, Scaling the data, Splitting train test data, Running Logistic Regression, Y prediction on test data, Class imbalance, Type 1 & Type 2 errors.

[NeurIPS’20] ⚖️ Build powerful ensemble class-imbalanced learning models via meta-knowledge-powered resampler. | 设计元知识驱动的采样器解决类别不平衡问题

😎 Everything about class-imbalanced/long-tail learning: papers, codes, frameworks, and libraries | 有关类别不平衡/长尾学习的一切：论文、代码、框架与库

Evaluating ensemble performance in long-tailed datasets (Neurips 2023 Heavy Tails Workshop)

Build a classification model for reducing the churn rate for a telecom company

A predictive model to anticipate customer churn in telecom. Using supervised ML techniques, it identifies at-risk customers based on usage patterns and service plans. Proactively retaining customers, reducing attrition costs.

A Julia toolbox with resampling methods to correct for class imbalance.

R and Data Files from my YouTube Channel

Repo for 2024 peak cherry blossom prediction competition

Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)

This homework leverages SMOTE for addressing class imbalance in a high-dimensional dataset, employing tree-based methods like random forest and XGBoost with model trees to enhance classification performance on the APS Failure at Scania Trucks dataset.

🛠️ Class-imbalanced Ensemble Learning Toolbox. | 类别不平衡/长尾机器学习库

Predict whether customer purchase a product or not in a session

[ICLR 2023] Official Tensorflow implementation of "Distributionally Robust Post-hoc Classifiers under Prior Shifts"

[ICDE'20] ⚖️ A general & effective ensemble framework for imbalanced classification. | 泛用，高效，鲁棒的类别不平衡学习框架

To deal with the class imbalance problem in multi-label learning with missing labels, we propose Class Imbalance aware Missing labels Multi-label Learning, CIMML. Our proposed method handles class imbalance issue by constructing a label weight matrix with weight estimation guided by how frequently a label is present, absent, and unobserved.

The project predicts the probability of loan default using various financial features of customer. I applied SMOTENN by combining SMOTE cand Edited Nearest Neighbor (ENN) to handle class imbalance. Logistic Regression, Random Forest and CATBOOST models have been apllied and evaluated based on accuray, F1 score, ROC-AUC score.

Play with ionosphere dataset