A Machine Learning project for Machine Learning Internship offered by InternshipStudio.

A full ML pipeline for customer churn prediction in telecom, banking, or SaaS. Includes robust data cleaning, automatic feature engineering, model training/tuning (Logistic Regression, RF, XGBoost), interpretability, and interactive dashboards for actionable business retention insights.

Extensive EDA of the IBM telco customer churn dataset, implemented various statistical hypotheses tests and Performed single-level Stacking Ensemble and tuned hyperparameters using Optuna.

Predicting Body Fat Percentage Using Machine Learning

I worked on this Live project while working as a Machine Learning Intern at Internship Studio that was offered by National Engineering Olympiad 5.0

Streamlit App for Node and Graph Classification and Explainability

DWSIM COOLSIM (IA) is an innovative application designed to simulate refrigeration and air conditioning systems and serves as an example for developing more complex systems for both refrigeration and chemical process simulation.

Modelling and prediction of default + deployment via AWS Sagemaker

Advanced Stacking with ensemble model

Production-ready ML regression system for restaurant rating prediction (0-5 stars) with exceptional performance: RMSE 0.123, R² 0.954, 96% accuracy within ±0.25 stars. Features FastAPI backend, interactive frontend, and comprehensive MLOps pipeline.

A deployable End-to-End machine learning model to predict loan default risk of new loan request for a financial services platform

Простенький монолит (кредитный скоринг)

Create a model that can accurately predict whether a user belongs to the HCP(Healthcare Professional) category or not. Based on server logs.

Machine learning classification system for early Parkinson's Disease detection using vocal biomarkers. Achieves 92.31% accuracy with XGBoost model analyzing voice characteristics including jitter, shimmer, and harmonic ratios from 195 clinical samples.

study of hyperparameter tuning methods

Create a machine learning model to help an insurance company understand which claims are worth rejecting and the claims which should be accepted for reimbursement.

DWSIM COOLSIM (IA) is an innovative application designed to simulate refrigeration and air conditioning systems and serves as an example for developing more complex systems for both refrigeration and chemical process simulation.

Thesis project for the MSc "Language Technology" of the National and Kapodistrian University of Athens (NKUA)

Predicting Saturation Vapour Pressure ~IML24

MoneyLion DS Assessment