Using SageMaker's linear classifier to detect fraud. Addressing class imbalance and setting target metrics for Precision and Recall

Class imbalance correction algorithm for multiple-instance data

Human or Robot? Predict if an online bid is made by a machine or a human.

Predicting categories of scientific papers with advanced machine learning techniques involving class imbalance in multi-label data and explainable machine learning.

Credit Card Fraud Detection using Machine Learning

Advanced NER Applications: Implementing KNN, Feed-Forward, and LSTM Models with Class Imbalance Reduction Techniques.

A collection of machine learning mini-projects.

Predict whether customers of a bank will subscribe to a term deposit and analyze customer behaviour based on the bank's historical telemarketing campaign records.

Machine Learning model for Credit Card Fraud Detection

Classification with imbalanced classes

Machine learning model for Credit Card fraud detection

Sampling-based class imbalance solutions for multiple-instance classification

Evaluate Machine Learning Models with Yellowbrick

Most existing classification approaches assume the underlying training set is evenly distributed but many real-world classification problems have an imbalanced class distribution, such as rare disease identification, fraud detection, spam detection, churn prediction, electricity theft & pilferage etc.

Application of Deep Neural Networks for Credit Card Fraud Detection System, using state-of-the-art techniques such as Autoencoders, Generative Adversarial Networks, and Convolutional Neural Networks.

jBVQ: Bayes Vector Quantizer for Java

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 objective of this analysis is to better understand the characteristics of Detroit Schools with elevated lead levels as identified via testing in 2016 by aggregating three publicly available data sources from the city of Detroit.

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

Udacity DAND Project: Identify fraudulent personalities from enron emails and dataset