Abstract: The population's life expectancy is a problem for the government or pertinent agency of a particular nation. A statistical measurement of the anticipated average lifespan of an organism is life expectancy. Data for the appropriate nation, including all required fields, must be gathered in order for the department to handle life expectancy in an efficient manner. This study analyses and forecasts trends in life expectancy using data analytics and machine learning approaches. Regression models are used in the study to find the major determinants of life expectancy as well as descriptive statistics to understand how long people live across various population groupings. The WHO data repository was used to gather the information, which was then retrieved from the Kaggle website, a reputable data science resource. The dataset contains variables including vaccination, mortality, economy, social factors, and other health-related variables. It covers the years 2000 to 2015 for 193 nations. These factors are taken into account when this study uses data analytics and machine learning to implement life expectancy. After examining numerous regression methods, the Random Forest Regressor was chosen since it generated the greatest accuracy among the models studied.