Prediction of air pollution hotspot to prevent post effects of pollution by comparing logistic regression with random forest.

This research evaluates the Logistic Regression (LR) and Random Forest (RF) algorithms, two popular statistical approaches for long-term pollution forecasting. The Parts and Methods: Logistic Regression may effectively predict air pollution better than other machine learning methods. Logistic Regression and Random Forest were used to create a framework for diagnosing air pollution to reduce its impacts. G power indicated that each group required 96 participants. Pretest power was 92%, and the sample size was 2 groups of 48 samples. The dataset showed that Logistic Regression predicted air pollution with 92% accuracy, outperforming Random Forest with a significance of 0.001(p=0.005). Logistic Regression trumps Random Forest in accuracy and precision. [ABSTRACT FROM AUTHOR]