Cervical cancer is the most frequent gynecological cancer that, if left untreated, seriously affects women. In order to provide the best possible cervical cancer forecasting, this study shows the advantages of feature selection approaches and presents a variety of classification algorithms. In order to help patients make educated decisions, the healthcare industry uses the vast amount of data from digital patient systems to forecast immune deficiencies syndrome and extract information. A health recommender system is used to make the content of the reports easier for patients to interpret. We use wrapper approaches with the K Nearest Neighbor (KNN) classifier for feature selection in the suggested framework, and Multi Objective Algorithm (MOA) has been found to work best is employed in the feature selection process of this system because it is an extremely effective evolutionary algorithm for choosing the crucial features comprising the least amount of complexity in contrast to other traditional feature selection techniques. The evaluation of this parameter served as the dataset for the application and precision of the cervical cancer risk classification.