Cervical cancer is the fourth most frequent cancer in women representing 7.9% of female cancers as stated by the World Health Organization. One of the leading causes of this has been the lack of effective early treatment. Therefore, early detection of cervical cancer is of utmost importance. The asymptomatic nature is the major challenge faced in the diagnosis of cervical cancer in the early stage. Machine learning has been of great help in many medical applications and can be used as a classifier in the early detection of the cancerous cells present in the cervix region of the uterus. In this paper, a survey and analysis of the various machine learning approaches that have been implemented for the diagnosis of cervical cancer is done. The survey paper draws a comparison of the various existing techniques for the prediction of cervical cancer using medical data and points out their advantages and shortcomings.