Predicting Life Expectancy using Machine Learning Approach through Linear Regression and Decision Tree Classification Techniques

Predicting someone's longevity requires looking at a broad variety of circumstances, making it a difficult and multidimensional task. There are a number of important factors that must be taken into account from a substantive perspective in order to provide an accurate prediction of life expectancy. Life expectancy is not a constant that can be calculated from a person's genes or other unchangeable characteristics. Instead, it is affected by a complex interplay of biological, psychological, and social elements, any of which may play a greater or lesser role depending on the context. For instance, lifestyle variables like smoking, alcohol use, and exercise levels, as well as access to healthcare, nutrition, and clean water, may all have a substantial influence on life expectancy. It is difficult to estimate a person's lifespan without considering a broad variety of characteristics, such as their socioeconomic status, access to healthcare, and way of life. Life expectancy prediction is a regression issue rather than a classification problem, however both linear regression and decision tree classification are useful machine learning approaches for making predictions. In this study, we apply a machine learning strategy to the problem of life expectancy prediction utilising linear regression and decision tree classification methods. According to the findings, the Decision Tree Classifier obtained 92% accuracy while the Linear Regression Classifier reached 96% accuracy.