Health Outcomes Prediction and Analysis Based on Air Quality Indicators
Project involves predicting future values and analyzing trends in air pollution levels and health impacts. The analysis includes grouping data by geographical location, year, and indicator levels to identify the most polluted areas and assess the health risks associated with different levels of air pollution.
The project uses machine learning algorithms, including the Gradient Boosting Regressor and RandomForestRegressor, to analyze air quality. The MultiOutputRegressor is used for predicting health outcomes based on air quality indicators, allowing for grouping data and making predictions based on multiple outputs. The tech stack includes Python for coding, libraries such as Pandas and Scikit-learn for data manipulation.
