Trying to recogize and predict fraud in financial transactions is a good example of binary classification analysis. A transaction either is fraudulent, or it is genuine. What makes fraud detection especially challenging is the is the highly imbalanced distribution between positive (genuine) and negative (fraud) classes.

Quantum ML for extremely imbalanced data

Fix data skew by packing into bins

Machine Learning Nano-degree Project : To help a charity organization identify people most likely to donate to their cause

Mixtures-of-ExperTs modEling for cOmplex and non-noRmal dIsTributionS

data engineering challenges and fun

Opportunities and challenges in partitioning the graph measure space of real-world networks

This project demonstrates building a classification model for imbalanced data. Feature engineering, feature selection and extensive EDA. Comparing of logistic regression, random forest and ADA Boost models are done before finalizing the best model.

A base possui informações obtidas de análises químicas de vinhos da mesma região da Itália, porém são provenientes de 3 diferentes cultivadores. A análise mostra a quantidade de 13 componentes achados em cada um dos 3 tipos de vinhos.

Official Implementation of ACMMM'21 paper "Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting"

Build predictive models on highly skewed data by selecting an example of fraudulent transactions in the financial institutions🚀

Space-Time Statistical Quality Control of Extreme Precipitation Observation

Predicting Time of Arrival for Food Delivery Service

Course Major Project of Pattern Recognition and Machine Learning( CSL2050 )

LambertW R package: Lambert W x F distributions and Gaussianization for skewed & heavy-tailed data

This repository contains data visualization programs on various datasets done using python.

Skin lesion image analysis that draws on meta-learning to improve performance in the low data and imbalanced data regimes.