This project implements a supervised machine learning classification system to predict Iris flower species (Setosa, Versicolor, Virginica) using sepal and petal measurements as input features. The model was developed in Python using Scikit-learn for dataset access (load_iris), train-test splitting, model training, and performance evaluation. Data handling and preprocessing were performed using Pandas and NumPy, and model accuracy was validated on test data to ensure reliable generalization. The trained model was serialized using pickle/joblib and integrated into a Streamlit dashboard (app.py), providing an interactive UI for real-time species prediction based on user inputs. This project demonstrates core machine learning concepts such as supervised classification, feature-based prediction, model evaluation, and basic deployment by combining ML logic with a lightweight web-based interface.