Utilizing machine learning models including logistic regression, random forest, gradient boosting, and neural networks to identify fraudulent credit card transactions. Dataset, consisting of PCA-transformed features and unbalanced classes, required precision-recall metrics for accurate evaluation. Developed in Python using TensorFlow and scikit.

Our project utilizes machine learning models to predict cardiovascular diseases (CVDs) by analyzing diverse datasets and exploring 14 different algorithms. The aim is to enable early detection, personalized interventions, and improved healthcare outcomes.

This is a master thesis project done by Ezgi Günbatar for Applied Data Science program at Utrecht University. The repository contains datasets and codebooks which are used in "The Role of Social Networks and Personal Characteristics in Shaping Fertility Intentions: A Multi-Method Machine Learning Perspective" study.

This repository contains Python scripts to train and deploy a Gradient Boosting Machine (GBM) classifier for predicting employee efficiency based on various features such as age, experience, education level, and average handling time. The model is implemented using scikit-learn and pandas libraries.

MSBoost is a gradient boosting algorithm that improves performance by selecting the best model from multiple parallel-trained models for each layer, excelling in small and noisy datasets.

Online course engagement prediction using Gradient boost classifier

Model to Predict if a customer will purchase a Travel Package

Fastag Fraud Detection Classification System

Simple and flexible classical ML module that can be used for recording baseline ML performance.

Diabetes is a medical disorder that affects how the body uses food for energy. When blood sugar levels rise, the pancreas releases insulin. If diabetes is not managed, blood sugar levels can rise, increasing the risk of heart attack and stroke. We used Python machine learning to forecast diabetes.

Machine Learning

This project aims to predict bank customer churn using a dataset derived from the Bank Customer Churn Prediction dataset available on Kaggle. The dataset for this competition has been generated from a deep learning model trained on the original dataset, with feature distributions being similar but not identical to the original data.

Loan Eligibility Prediction Model: A machine learning application to predict loan approval based on applicant data. Includes a web interface for submitting loan applications and receiving predictions. Built with Python and Jupyter Notebook.

This project detects spam messages in SMS, including those written in regional languages typed in English. It uses an extended SMS dataset and applies the Monte Carlo method with various supervised learning algorithms to improve spam detection.

Ce projet est une proposition de solution au Rakuten Data Challenge. L'objectif est de mettre en œuvre différentes méthodes de Machine Learning et Deep Learning pour résoudre le problème.

This project analyzes employee attrition data to uncover key factors, predict turnover, and develop strategies for retention, ultimately enhancing organizational stability and performance.

a predictive model for bankruptcy risk assessment using machine learning algorithms and financial indicators extracted from company financial statements

This project evaluates logistic regression, random forest, decision tree, and gradient boosting classifier models for fake news detection. Using labeled data, it analyzes accuracy, confusion matrices, and ROC curves to understand each model's effectiveness in discerning between real and fake news.

Using various machine learning models (Logistic Regression, Gaussian Naïve Bayes, KNN, Gradient Boosting Classifier, Decision Tree Classifier, Random Forest Classifier.) to predict whether a company will go bankrupt in the following years, based on financial attributes of the company; Addressed the issue of imbalanced classes, different importance

A machine learning application, deployed using Flask, is designed to identify the presence of kidney disease in patients by analyzing various medical features.