Ovaries are influenced by the common hormonal ailment known as Polycystic Ovary Syndrome (PCOS). There are sometimes irregularities in menstrual cycles, elevated levels of androgens (the hormone responsible for reproduction in males), and several small cysts on the ovaries. These factors can lead to symptoms like acne, greasy skin, weight gain, excessive hair growth, along difficulties getting pregnant. If this sickness is not identified in a timely way, it may result in serious health issues. To solve the problem, this work employs a comparative analysis of categorization and prediction strategies. It also proposes the utilization of machine learning techniques to build an application for early PCOS prediction based on a certain age segment. Support Vector Machines (SVM), Random Forest (RF), and Logistic Regression (LR) are some of the machine learning techniques used to predict PCOS. Kaggle provides the necessary dataset. LR is able to determine with the highest accuracy, in contrast to other state-of-the-art algorithms.