Credit Card Fraud Detection using ML: IEEE style paper + Jupyter Notebook

Credit Card Fraud Detection Project

This repository contains the code of our published work in IEEE JBHI. Our main objective was to demonstrate the feasibility of the use of synthetic data to effectively train Machine Learning algorithms, prooving that it benefits classification performance most of the times.

A fraud detection project that processes user or credit card data using machine learning and deep learning algorithms.

Location information about commuter activities is vital for planning for travel disruptions and infrastructural development. The Mobility Sensing Project aims to find innovative and novel ways to identify travel patterns from GPS data and other multi-sensory data collected in smartphones. This will be transformative to provide personalised trave…

MATLAB code for augmenting small datasets using EigenSample

This repository contains the code for baseline model replication along with all experiments and used datasets as part of the master's thesis on the topic "Detecting Dyslexia Using Deep Learning".

Data Science Case Study

The aim of this project is to predict fraudulent credit card transactions with the help of different machine learning models.

The computing scripts associated with our paper entitled "Oversampling Highly Imbalanced Indoor Positioning Data using Deep Generative Models".

This repository contains the code, documentation, and datasets for a comprehensive exploration of machine learning techniques to address class imbalance. The project investigates the impact of various methods, like ADASYN, KMeansSMOTE, and Deep Learning Generator, on classification performance while effectively demonstrating benefits of pipelining.

Continuing with telemarketing model to predict campaign subscriptions in a portuguese bank institution. For this project I have evaluated the performance of four resampling techniques and selected the best one to implement the logistic model.

Use Random Forest to prepare a model on fraud data. Treating those who have taxable income <= 30000 as "Risky" and others are "Good" and A cloth manufacturing company is interested to know about the segment or attributes causes high sale.

The case study is a traditional supervised binary classification problem based on the UCI Machine Learning Repository "adult" dataset.

Classification of Obesity Status in Indonesia Using XGBoost & ADASYN-N Method

Classify Indonesian Obesity Status using ADASYN-N and Random Forest algorithm

Detecting Abnormal Markets - Early Warning Systems

To predict whether the customers will subscribe to the system after 1-month free trial or not.

Build, train and compare performances of multiple binary classification machine learning model techniques to detect credit card fraudulent transactions.