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

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

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.

This project focuses on predicting individual medical insurance charges using demographic, lifestyle, and health-related variables. The workflow includes Exploratory Data Analysis (EDA), interactive data visualization using Streamlit, and Machine Learning model development to accurately estimate healthcare costs.

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.

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

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.

End-to-end analysis of SpaceX launch data: mission success prediction, launch trends, customer diversity, and payload optimization. Complete ML pipeline with EDA, feature engineering, and deployment. this project is the final capstone project to obtain the IBM data science professional certificate.

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.

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.

Analyzes real Linux update logs and uses machine learning to assess update stability and risk.

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

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.

"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.

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

Ds mL starter

A production-grade machine learning system for detecting phishing websites using 30 security features.

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

머신러닝 엔지니어 실무

No description provided.

Data Science, Applications and Pipelines

Master's machine learning projects

Titanic Survival Prediction – Random Forest achieved 83.2% accuracy in predicting passenger survival. Movie Success Prediction – XGBoost delivered 0.89 R² score for box office revenue forecasting. Iris Flower Classification – SVM reached 96.7% accuracy in species classification.

🎯 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.

Here we create a ML Pipeline that applies transformation to columns of a dataset and then a Linear Regression. Finally we estimate the error and compare the transformed and raw data to check if the pipeline is in fact improving the model.

Clustering-based ML on the stock dataset using Kmeans, DVC, and MLflow

This project explores how AutoML simplifies machine learning workflows by automating model selection, hyperparameter tuning, and evaluation, comparing tools like TPOT, H2O, and AutoKeras, and culminating in a custom-built AutoML system from scratch.