RANDOM FOREST REGRESSION MODEL FOR ESTIMATION OF NEONATAL LEVELS IN NIGERIA C. Managwu * , D.Matthias ** , N. Nwaibu ** *,** Dept. of Computer Science, Rivers State University, Port Harcourt, Nigeria *Corresponding Author: Chidozie.managwu@gmail.com ______________________________________________________________________________ Abstract Health is considered to be a fundamental necessity of all living beings, particularly humans, hence its availability is a critical component of the Human Development Index (HDI) measurement of human health. Neonatal (NMR) and infant (IMR) mortality rates are not subjects that take too much time or attention for most of us on our day-to-day thinking, but they are also vital to guaranteeing our quality of living. Evidence-based awareness of infant mortality patterns and drivers can support correct strategies required to counter the threat. Nigeria's attempts to minimize under-five mortality have been skewed against neglect of neonates in favor of childhood mortality, and as such the literature lacks adequate knowledge to estimate neonatal rates accurately. Whereas studies have shown that in the neonatal period, about half of infant deaths occur. Awareness of the rate of neonatal deaths as well as neonatal mortality determinants are important for the design of intervention programs to improve neonatal survival. Hence, this research was conducted to apply Random Forest Regression in predicting neonatal death rates to help better prepare healthcare systems for future occurrences. This model will be educated using the existing dataset of actual neonatal death rates from 1970 through to 2018. This model may be used to predict neonatal death rates and thus help prepare them adequately to reduce risk by providing medical treatment, thus reducing infant mortality levels. Key Words: Neonate, Neonatal Mortality, Big Data , Human Activity Pattern.. 1. INTRODUCTION Having automated, high-quality results predictions to ensure fair access to knowledge regardless of where they are located, device and current state of health is of great importance. Specifically, reliable forecasts of future performance are a high priority for companies, because they are important for smooth operation, customer loyalty and explain how to manage them, functionality and product safety features. Highly imprecise forecasts can produce very extreme results in the field. Cooperation between undertakings may also suffer from misunderstandings due to bad predictions. Considering that predictions of machine learning are a very complex problem, the output provided by predictive machine learning models still needs to be continuously retrained and accepted to ensure the required quality. Easy use of software to forecast health outcomes therefore moves the question from growth to evaluation and correction, but does not address it. Consequently, the assessment of the prediction model represents a significant step in minimizing time and costs for companies, and in finding an appropriate way to ensure that the best solution is used as applicable to the application. Access to computerized systems which make near-correct predictions based on previously trained data is still revolutionary. Regarding this problem, it is necessary to be able to rank the quality of a given prediction-acceptability can not be assured of a predicted value. Due to their high quantity of in-selling company which further enhances the ability to automatically predict results, the technical documentation places special emphasis on it. Nowadays companies manage the specified prediction problem by outsourcing this task to outside sources. Since the person requesting these predictions does not know the source of the