Machine Learning projects (image classification, predictive modelling)

Predicting whether a customer is happy based on the results from a survey.

This project leverages data from 383 thyroid cancer patients over 15 years to develop a model to predict propensity for reoccurrence based on certain features. This work extends and further explores different model types to emerge with the best predictor model - and save more lives

A fake news detection app leveraging Ensemble ML models and NLP context-analysis to evaluate the credibility of news articles by cross-referencing claims with reliable databases.

Pusion (Python Universal Fusion) is a generic and flexible framework written in Python for combining multiple classifier’s decision outcomes.

Final Project on how to detect domains that were generated using "Domain Generation Algorithm" (DGA). The idea is to tell DGA-generated and non-DGA-generated domains apart using a combination of linguistic features by transforming raw domain strings to ML features.

Analyze, visualize and predict customer churn using Machine Learning

Developed and evaluated machine learning and deep learning models for detecting financial fraud.

Predictive Modeling for Cardiovascular Disease Prevention

A multiNER websevice based on the KB's multiNER

RED CoMETS: an ensemble classifier for symbolically represented multivariate time series

This notebook explores comprehensive machine learning analysis on a rock dataset, covering attribute distribution analysis, outlier identification using statistical values and visualizations like scatter plots,and applying Multinomial Logistic Regression,Support Vector Machines, Random Forest classifiers,Ensemble learning,hyperparameter optimizatio

A summary of my approaches for the Diabetic Retinopathy Image Classification Dataset

Dynamic Ensemble Diversification

An ensemble model created to classify images of currencies of 211-different classes. Winning entry for the https://www.kaggle.com/competitions/currency-prediction-challenge with around 88% accuracy.

Two ensemble models made from ensembles of LightGBM and CNN for a multiclass classification problem.

Machine learning diabetes prediction mini project

This repository contains the code for a web-based diabetes prediction application using a machine learning model. The application is built using Flask and allows users to input various health parameters to predict the likelihood of diabetes using ensemble voting classifier.

This project focuses on predicting the likelihood of a person having diabetes based on various health-related attributes using Random Forest Algorithm