Alzheimer’s is a type of dementia that progressively destroys memory cells and other important mental functions. It is a degenerative process involving different stages and it is critical to predict the progression for developing lifestyle change guidance or treatments to slow it down given that there is no cure. Although there has been lot of research going on for developing prediction models using deep learning and machine learning techniques focusing on the severity staging prediction of Alzheimer’s Disease (AD), this paper investigates mainly on the time factor for progressing to the next stage. A machine learning model is applied to analyzing the factors contributing to the progression using the clinical and neuropsychological data provided by the National Alzheimer’s Coordinating Center. In this study, given the metrics to assess the AD stage and the clinical diagnoses of the patient’s historical visits, the number of months it takes for a patient to progress to the next stage is predicted. The most important factors that contribute to the progression of the disease to the next stage are uncovered, aimed at helping AD patients weaken their disease progression.