Cervical cancer is the second most common type of cancer that is found in the women worldwide. Generally, cancer caused due to irregular growth of cells in a particular area that or have the potential to spread to the other parts of the body as well. Identification of a cervical cancer test is an examination of the tissue taken from a particular region, which might contain cancerous cells through biopsy, is exceptionally challenging because these types of cells does not offer unusual color or texture variants from the standard cells. To identify the abnormalities in human cell the high-level digital image processing technologies are already present in the market which very costly concerning the money. Therefore, we are proposing the model which going to classify whether a female patient has cervical cancer or not. We are using various attributes from real-life and performing a feature selection algorithm Recursive Feature Elimination (RFE). Afterward, making classification models using three machine-learning algorithms like K-Nearest Neighbour (KNN), Random Forest and Multilayer Perceptron (MLP), MLP is a type of the Artificial Neural Network (ANN) algorithm whereas KNN and Random Forest is a supervised type of algorithm. Copyright © 2019 American Scientific Publishers All rights reserved.