Gestational Diabetes Mellitus is a primary health issue during pregnancy, potentially leading to other complications during labor and effects on both mother and child. This study aims to use various machine learning techniques to predict GDM using the Pima Indians Diabetes dataset, which has 786 samples. We used several machine learning algorithms including Logistic regression, XG Boost, Random Forest, Support Vector Machine (SVM), and Naive Bayes, for classifying individuals at risk of developing GDM. The dataset underwent various preprocessing techniques like normalization, handling missing values and feature engineering including SMOTE augmentation and log transformation. The objective is to determine the effectiveness of these models in identifying individuals at risk of developing GDM. Gestational Diabetes Mellitus (GDM) is a prevalent health condition that can develop during pregnancy, presenting potential risks to both the mother and the child, including complications during labor and increased likelihood of developing Type 2 diabetes later in life. Early and accurate identification of individuals at risk of GDM is crucial for timely intervention and management, which can significantly improve health outcomes. This study aims to predict the risk of GDM using various machine learning techniques applied to the Pima Indians Diabetes dataset, which consists of 786 samples with multiple health-related variables.