Predictive Maintenance System Using Machine Learning

Developed a Machine Learning project for predictive maintenance using industrial sensor data to predict machine failures before they occur.

The project included data cleaning, exploratory data analysis (EDA), feature engineering, handling class imbalance, and training classification models using Python and Scikit-learn. Different algorithms were tested and evaluated using metrics such as Recall, F1-Score, and PR-AUC to improve failure detection performance.

The goal of the project was to help reduce unexpected machine downtime and support data-driven maintenance decisions in industrial environments.

**Tools & Technologies:** Python, Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, XGBoost.