Air Pollution Comparison RFM Model Using Machine Learning Approach

Air pollution is related to the economy in every country nowadays. This research uses Air polluted data set off a month in Seoul, South Korea. According to the Air quality index, the feature provides information on gas sensors Such as Sulfur dioxide (SO2), Nitrogen dioxide(NO2), Ozone (O3), Carbon monoxide(CO), particulate matter PM10, PM2.5, etc. The Air quality monitoring systems have been based on RFM (Recency, Frequency, Monetary) structure in machine learning techniques to predict air pollutants concentration in urban areas. This paper evaluated Air pollution data for different neighbours in clustering values. In data, collect basic information also data inspection has described. Obtaining accurate predictions requires tuning different values from the neighbour of clustering algorithms used in the k-means algorithm. K-means can only utilize when the data objects extend in the Euclidean term. Here dataset performance observes by K-Means clustering with the elbow method in optimal numbers. In the simulation, the correct level of knowledge has been on Air pollution data and higher accuracy—this issue using the tool for analysis with Google co-lab and Python. The cluster value compared with these different types of optima values discussion parts will help plan to execute the predicted machine learning model.