Scalable Machine Learning and Deep Learning, Final Project, 2023/2024

Fraudfinder: A comprehensive lab series on how to build a real-time fraud detection system on Google Cloud

This provider contains operators, decorators and triggers to send a ray job from an airflow task

Designing your first machine learning pipeline with few lines of codes using Orchest. You will learn to preprocess the data, train the machine learning model, and evaluate the results.

Machine Learning Pipeline to categorize emergency messages based on the needs communicated by the sender.

SalaryAi is a machine learning-powered web application that predicts employee salaries based on input features like age, gender, education level, job title, and years of experience. Built with FastAPI, it includes a sleek frontend interface and uses U.S. salary data for predictions.

Scalable SageMaker pipeline reducing model training time by 40% for enterprise ML.

Created Disaster response pipelines and Web App for classifying text messages received during disaster into response categories, reducing the potential reaction time of disaster response organizations.

To learn about the key components of MLOps, APIs and API designs.

The Loan Status Prediction Model predicts loan approval based on applicant details like income, credit history, and loan amount. It uses data preprocessing, an SVC model, and achieves around 79% accuracy. The trained model is saved for future use.

an ML pipeline was built to identify WMSD risk from workers’ images using ANN

Spam-Ham(not spam)-App Using Naive Bayes ml algorithm. Check it out in Hugging Face Spaces.

Ds mL starter

Built a production-ready machine learning pipeline using Scikit-learn to predict customer churn. Includes full preprocessing, model tuning with GridSearchCV, evaluation, and pipeline export with joblib.

"End-to-End Machine Learning Pipeline Creation Using DVC: A comprehensive MLOps solution on GitHub." This GitHub repository showcases the implementation of an end-to-end machine learning pipeline using DVC (Data Version Control) for efficient data management and MLOps practices. The pipeline covers the entire machine learning workflow.

This study analyzes a dataset of experimental measurements conducted at the Politecnico di Milano. The goal is to predict internal resistance under different conditions using machine learning pipelines.

A Sagemaker e2e multi-model pipeline that can tune multiple models on separate datasets and deploy them to a single endpoint.

머신러닝 엔지니어 실무

Master's machine learning projects

🎯 Employee Salary Prediction | IBM Internship Project - Predict whether an individual earns more than $50K/year using machine learning. Built during my IBM internship, this end-to-end project includes model training, evaluation, and deployment with Streamlit UI, featuring visual insights and batch predictions.