One of the prevalent diseases that tend to have elderly patients has been the Alzheimer Disease (AD). It is a neurological disease where the brain cells start to deteriorate. As the disease progresses it eventually leads to the death of the brain cells. This result shows various problems like memory loss change in behavior pattern and many more. The most challenging problem has been in predicting an early diagnosis of AD in patients. The disease is predicted based on the various features of the patient. Feature selection has been one of the important steps in predicting the disease. This paper takes the OASIS data set and implements the different algorithms and proposes the. The proposed model identifies the salient feature by recursively considering smaller and smaller sets of the features. The classification has been done for evaluating the feature selection. The performance metrics shows improved score after applying feature section concept. The model is found to have a good accuracy level when compared to other models.