Polycystic Ovarian Syndrome (PCOS) is a general hormonal condition that women face especially during their reproductive years. Hormonal conditions like ovarian cysts, irregular menstrual periods, facial hair growth are among their symptoms. PCOS is one of the most worrisome disorders of modern times because it is so destructive and can have a major influence on women's reproductive lives and also impacts their daily lifestyle. The dataset contains information depends on many different factors such as age, weight, marital status, testosterone levels, body mass index (BMI), and irregular menstruation. Numerous machine learning methods like Support Vector Machine, Random Forest, and Logistic Regression were utilized in an effort to determine the optimal model for PCOS prediction. The purpose of this paper is to establish a trustworthy predictive model in the early identification of PCOS affecting females. The results offer a useful and accurate method for PCOS prediction that have a significant impact on women's health. Early risk assessment can help the females in timely treatment plans and improved results. Dataset of 541 women was obtained from Kaggle. It was ascertained that the best model for predicting PCOS was logistic regression.