Smoking Predictor

Abstract

Data Mining can be defined as the use of complex tools of data analysis to discover previously unknown relationships and patterns in large datasets. Therefore, data mining comprises techniques that enable more process than data collection and management, including data analysis and prediction. Healthcare databases have huge amounts of data, and with effective analysis, a great deal of hidden knowledge can be discovered. Therefore, predictive analytics can be particularly useful for analyzing and extracting hidden knowledge in large amounts of data obtained from smokers. Predictive Analytics with data mining has found an application in the medical sector. Data mining in healthcare organizations can transform the raw data held by the organization into useful knowledge with minimal intervention by the user. It also can help to discover new healthcare knowledge for clinical and administrative decision making, as well as producing scientific hypotheses from large sets of experimental data and clinical databases. In the analysis of smoking characteristics, there are a limited number of cases where prediction by data mining has been well utilized. A review on the subject reveals that there is an apparent lack of theoretical and empirical systems that address how this research can be used to understand a person’s smoking possibility in the near future. This study aims to build a self-developing system for human health using a data mining technique to predict smoking and help to determine the humans to stay safe. The system is based on a continuous acquisition of data, thereby improving its results regularly.