Air Quality Classification
Data Science & Analyst
About The Project
This project focuses on analyzing and classifying air quality levels based on environmental and pollution-related parameters. Using machine learning classification models, we aim to predict air quality categories and gain insights into contributing factors such as temperature, humidity, population density, and pollutant concentrations.
Tools & Libraries : Python, Google Colab, Pandas, Numpy, Seaborn, Matplotlib, Scikit-Learn, XGBoost.
Achievements
Achieved 96.3% classification accuracy in predicting air pollution levels using XGBoost, outperforming other models (Random Forest & Logistic Regression).
Demonstrated effective model selection and evaluation by conducting comparative analysis across multiple algorithms.
Showcased practical ML deployment insight by recommending XGBoost as the optimal model for real-world air quality prediction based on performance metrics.
Links
azzriala@gmail.com
+6287872788220
