A sentiment analysis using SPAM/HAM Text Classification data using Support Vector Machines. Utilizes different variations of the Synthetic Minority Oversampling Technique (SMOTE-SVM, SMOTE-KNN).

Established a supervised machine learning model trained and tested on credit risk data through a variety of methods to establish credit risk based on a number of factor

Implementation of Neural Networks to Forest Cover Type Discrimination

Using skills in data preparation, statistical reasoning, and machine learning, real-world challenges of credit card risk are assessed and solved.

This dataset contains information on default payments, demographic factors, credit data, history of payment, and bill statements of credit card clients in Taiwan from April 2005 to September 2005.

Разработка алгоритма привлечения новых клиентов банка

Predicting the churn of customers in a Telecom company using classification algorithms.

Player Rating System in Soccer using Machine Learning

Business Problem Overview In the telecom industry, customers are able to choose from multiple service providers and actively switch from one operator to another. In this highly competitive market, the telecommunications industry experiences an average of 15-25% annual churn rate. Given the fact that it costs 5-10 times more to acquire a new cust…

Training XGBoost ML model to detect credit default risk. Used SMOTE technique for handling unbalanced data. Evaluation of model trained on unbalanced dataset vs SMOTE generated dataset

This repository contains code that was used to predict employee attrition using machine learning methods.

As the there are couple of classification algorithms in supervised machine learning so some of them as here..

Este proyecto consiste en la detección de fraudes utilizando machine learning, datos desbalanceados y técnicas de muestreo.

This was a comprehensive project completed as part of the Data Science PG Programme. This covers classification algorithms over a dataset collected on health/diagnostic variables to predict of a person has diabetes or not based on the data points. Apart from extensive EDA to understand the distribution and other aspects of the data. Pre-processi…

Supervised Machin Learning Analysis using scikit-learn and imbalanced-learn libraries.

This study uses predictive analytics to detect stroke risk factors early, aiming to reduce occurrences. By analyzing risk factors with machine learning, it uncovers patterns and correlations. Models such as Logistic Regression, KNN, Decision Trees, Random Forest, and Neural Network.

Supervised scikit-learn machine learning models using several sampling techniques.

Objective of the classification goal is to predict the likehood of a liability customer buying personal loans