A company managing tourist real estate aims to offer a transfer service. This project uses logistic regression to analyze customer data and identify profiles most likely to purchase the service, enabling targeted early notifications to increase conversion and improve customer experience.

Predictive modeling for stroke, to identify patients at higher risk than others, to deploy more effective preventive measures; more selective lifestyle correction and risk factor reduction efforts.

This study presents a comparative analysis of static and dynamic ensemble learning for predicting myocardial infarction mortality. To mitigate the challenges of class imbalance, the research implements a comprehensive cost-sensitive framework that operates at the data, algorithmic, and evaluation levels.

A Python Package to Create Synthetic Tabular Data

Baudrate Generator (Standard and 16x Oversampling) using Verilog along with Verification

A question-answering project focused on handling imbalanced datasets through advanced oversampling techniques.

Official implementation of Bagging Folds using Synthetic Majority Oversampling for Imbalance Classification

Oversampling for Imbalanced Learning with Missing Values

DAB-SMOTE: A Python implementation of Density-Aware Borderline SMOTE for handling imbalanced datasets. It combines noise removal, DBSCAN clustering, and boundary analysis to generate high-quality synthetic samples.

Predicting employee attrition using 5 machine learning algorithms on 3 versions of the dataset.

🗂 Split folders with files (i.e. images) into training, validation and test (dataset) folders

A machine learning classification project for predicting diabetes using medical data with an imbalanced target variable. The project includes class imbalance handling using oversampling and undersampling techniques, model building with Logistic Regression and Decision Tree classifiers, and performance evaluation

Multi-purpose data analysis framework based on Bayesian networks and Causal models

A curated set of implementations, experiments, and notes exploring algorithms and techniques in machine learning.

Implementation of novel oversampling algorithms.

Dealing with class imbalance problem in machine learning. Synthetic oversampling(SMOTE, ADASYN).

Oversampling-Guided Search for Evolutionary Multiobjective Optimization

Financial distress prediction from Kaggle

Decision Tree and Random Forest which are supervised Machine Learning models were used to train for threat detection on a network. Challenge faced in this dataset: Imbalanced data which caused high accuracy and low precision leading to model incorrectly identifying threats.